# Graph Mining

Graph mining is the use of data-mining techniques to find patterns and relationships in collections of graphs, including graph algorithms and analysis.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Static Attribution of Android Residential Proxy Malware Using Graph Kernels

DevFeed: [Static Attribution of Android Residential Proxy Malware Using Graph Kernels](<https://devfeed.tech/articles/static-attribution-of-android-residential-proxy-malware-using-graph-kernels-143101.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2604.27302>)

Author: Peter Clark, Yong Guan, Zhonghao Liao

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [residential proxy network](<https://devfeed.tech/topics/residential-proxy-network.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [Android Security](<https://devfeed.tech/topics/android-security.md>)

Tags: [android](<https://devfeed.tech/tags/android.md>), [attribution](<https://devfeed.tech/tags/attribution.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [graph](<https://devfeed.tech/tags/graph.md>), [kernels](<https://devfeed.tech/tags/kernels.md>), [malware](<https://devfeed.tech/tags/malware.md>), [proxy](<https://devfeed.tech/tags/proxy.md>), [residential-proxy](<https://devfeed.tech/tags/residential-proxy.md>), [static](<https://devfeed.tech/tags/static.md>)

### AI overview

The study attributes Android residential proxy apps to one of four commercial networks using static analysis of control-flow and function-call graphs plus behavioral signatures. On 3,365 labeled apps, Weisfeiler-Lehman graph-kernel features, alone or combined with binary capability vectors, were evaluated across classifiers using five-fold DEX-grouped cross-validation. SGD reached a macro F1 of 0.985 on the expanded dataset. Automatically generated Yara rules provided an explainability aid, with per-family accuracy up to 88.45% after non-discriminative signatures were filtered. The authors also report that 51.4% of sampled apps still available through APKPure contained proxy SDK code, and identify 23 developers with other apps containing this functionality. These findings are from the abstract; it does not provide further methodological detail.

### Source excerpt

arXiv:2604.27302v2 Announce Type: replace Abstract: Android residential proxy applications represent a growing class of potentially-unwanted programs (PUPs) that covertly route third-party traffic through end-user devices, enabling ad fraud, credential abuse, and evasion of geolocation controls by sophisticated threat actors. Attributing an unknown APK to a specific proxy network remains challenging due to code reuse, SDK embedding, and obfuscation across proxy families. We present a static-analysis pipeline for automated proxyware family attribution, extracting graph-structured representations (control-flow and function-call graphs) and behavioral signatures from a labeled corpus of 3,365 Android proxy apps spanning four commercial proxy networks. We evaluate Weisfeiler-Lehman graph kernel features alone and fused with binary capability vectors across multiple classifiers. Using 5-fold DEX-grouped cross-validation to prevent data leakage, SGD achieves a macro F1 of 0.985 on the expanded dataset. To support explainability, we map classifier decisions to automatically generated Yara rules, achieving per-family accuracies up to 88.45\% after filtering non-discriminative signatures. Finally, we discuss these results in the context of the broader ecosystem. We find that from the expanded dataset, the majority of applications (51.4\%) still available through APKPure still contain embedded proxy SDK code. Further analysis of developer accounts reveals that 23 developers are responsible for other applications also containing such functionality, suggesting continuous and ongoing commercial relationships between proxy providers and developers.

## Auditing Path-Specific Fairness Across Causal Discovery Algorithms: A Heart Failure Case Study

DevFeed: [Auditing Path-Specific Fairness Across Causal Discovery Algorithms: A Heart Failure Case Study](<https://devfeed.tech/articles/auditing-path-specific-fairness-across-causal-discovery-algorithms-a-heart-failure-case-study-142512.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2603.15926>)

Author: Nitish Nagesh, Elahe Khatibi, Thomas Hughes, Mahdi Bagheri, Pratik Gajane, Amir M. Rahmani

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [responsible-ai](<https://devfeed.tech/topics/responsible-ai.md>), [causality](<https://devfeed.tech/topics/causality.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [allows](<https://devfeed.tech/tags/allows.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [assessment](<https://devfeed.tech/tags/assessment.md>), [auditing](<https://devfeed.tech/tags/auditing.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [bias](<https://devfeed.tech/tags/bias.md>), [can](<https://devfeed.tech/tags/can.md>), [case](<https://devfeed.tech/tags/case.md>), [case-study](<https://devfeed.tech/tags/case-study.md>), [choice](<https://devfeed.tech/tags/choice.md>), [contribution](<https://devfeed.tech/tags/contribution.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [failure](<https://devfeed.tech/tags/failure.md>), [fairness](<https://devfeed.tech/tags/fairness.md>), [study](<https://devfeed.tech/tags/study.md>)

### AI overview

The study finds that causal discovery algorithm choice can change path-specific fairness estimates and the fairness-utility trade-off for heart failure risk models. Using an expert-elicited graph benchmark, it reports that ICA-LiNGAM had the lowest structural Hamming distance and highest recall, while GES had the highest precision. The mediated effect on ejection fraction differed by 1.2 percentage points between the original and discovered graphs, contributing to variation in the fairness-utility ratio. The authors argue these findings support fine-grained, discovery-aware fairness audits; the supplied abstract does not detail the methods or broader limitations.

### Source excerpt

arXiv:2603.15926v2 Announce Type: replace-cross Abstract: Causal discovery is increasingly applied to healthcare data, where the recovered relationships can encode biased pathways that propagate to downstream prediction. Path-specific fairness analysis, through direct, indirect, and spurious effect decompositions along with fairness-utility ratio assessment allows bias quantification and associated prediction cost. However, existing evaluations of causal discovery under fairness constraints have largely used non-clinical datasets and have not separated the contribution of confounders from that of mediators, leaving open how discovery-algorithm choice propagates through path-specific fairness to the utility trade-off in clinical settings. This work addresses that gap by establishing an expert-elicited causal graph benchmark for the heart failure clinical records dataset and tracing discovery algorithms through composite, per-variable fairness decompositions and fairness-utility ratio. ICA-LiNGAM achieves the lowest structural Hamming distance and highest recall, while GES achieves the highest precision. For path-specific effects, there was a 1.2 percentage-point difference in the mediated effect on ejection fraction on overall causal fairness between the original and discovered graphs. This ultimately led to variations in the fairness-utility ratio highlighting need for fine-grained evaluation. These results indicate that discovery-aware, path-specific fairness evaluation is consequential in clinical settings and warrants inclusion in routine auditing of clinical risk models.

## DLS: Dual-Logic Graph Neural Networks with Chaos-Fuzzy Residuals for Robust Link Prediction

DevFeed: [DLS: Dual-Logic Graph Neural Networks with Chaos-Fuzzy Residuals for Robust Link Prediction](<https://devfeed.tech/articles/dls-dual-logic-graph-neural-networks-with-chaos-fuzzy-residuals-for-robust-link-prediction-141793.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22607>)

Author: Mohammad Mehdi Keikha, Abolfazl Nadi

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [chaos](<https://devfeed.tech/tags/chaos.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-si](<https://devfeed.tech/tags/cs-si.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [discrimination](<https://devfeed.tech/tags/discrimination.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [experimental](<https://devfeed.tech/tags/experimental.md>), [feature](<https://devfeed.tech/tags/feature.md>), [filter](<https://devfeed.tech/tags/filter.md>), [framework](<https://devfeed.tech/tags/framework.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-mining](<https://devfeed.tech/tags/graph-mining.md>), [graph-neural-networks](<https://devfeed.tech/tags/graph-neural-networks.md>), [inductive](<https://devfeed.tech/tags/inductive.md>), [link](<https://devfeed.tech/tags/link.md>), [logic](<https://devfeed.tech/tags/logic.md>), [map](<https://devfeed.tech/tags/map.md>), [networks](<https://devfeed.tech/tags/networks.md>), [neural-networks](<https://devfeed.tech/tags/neural-networks.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [robust](<https://devfeed.tech/tags/robust.md>)

### AI overview

DLS (Dual-Logic SAGE) targets over-smoothing in message-passing link prediction, especially on heterophilous graphs where nearby nodes may have dissimilar features. Its dynamic residual pipeline uses a Logistic Map to diversify node features, then fuzzy-logic soft-thresholding to filter noise and retain higher-confidence signals. The abstract reports significantly better results than state-of-the-art baselines in heterophilous settings and competitive efficiency on homophilous graphs, based on diverse benchmarks; it provides no benchmark names or quantitative results.

### Source excerpt

arXiv:2611.22607v1 Announce Type: new Abstract: Link prediction is a fundamental task in graph mining, critical for applications ranging from biological interaction discovery to recommender systems. While Message Passing Neural Networks (MPNNs) have achieved state-of-the-art results, they are fundamentally limited by the inadvertent suppression of high-frequency signals, as the recursive aggregation that stabilizes structural learning inherently leads to over-smoothing, rendering node representations indistinguishable in deep layers. This limitation is particularly severe in heterophilous graphs, where structural proximity does not imply feature similarity. In this paper, we propose DLS (Dual-Logic SAGE), a novel inductive framework designed to break the over-smoothing barrier via a "controlled instability" mechanism. Unlike conventional methods relying on static structural heuristics, DLS introduces a dynamic residual pipeline. First, a Chaotic Injection Module utilizes the Logistic Map to diversify the feature manifold, exploiting sensitivity to initial conditions to separate topologically similar but semantically distinct nodes. Second, to mitigate the aleatoric uncertainty introduced by chaotic dynamics, a Fuzzy-Logic Gating Mechanism applies soft-thresholding to filter noise and retain only high-confidence signals. Experimental results on diverse benchmarks demonstrate that DLS effectively balances feature discrimination with robustness, significantly outperforming state-of-the-art baselines in heterophilous settings while maintaining competitive efficiency on standard homophilous graphs.

## Evidence Diet: When Graph Evidence Helps LLMs Rank Competing Candidates

DevFeed: [Evidence Diet: When Graph Evidence Helps LLMs Rank Competing Candidates](<https://devfeed.tech/articles/evidence-diet-when-graph-evidence-helps-llms-rank-competing-candidates-137620.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20837>)

Author: Yuchong Hu, Zhao Zhang, Ziyao Zhao, Haoyu Wang, Jing Xiao

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>)

Tags: [attribution](<https://devfeed.tech/tags/attribution.md>), [books](<https://devfeed.tech/tags/books.md>), [counts](<https://devfeed.tech/tags/counts.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [development](<https://devfeed.tech/tags/development.md>), [graph](<https://devfeed.tech/tags/graph.md>), [information-retrieval](<https://devfeed.tech/tags/information-retrieval.md>), [llms](<https://devfeed.tech/tags/llms.md>), [rank](<https://devfeed.tech/tags/rank.md>)

### AI overview

On Amazon Books and MovieTV, LLM rankers respond more to which supported candidate receives graph evidence than to matched item substitutions: swapping user-level evidence degrades ranking, and exchanging intact count pairs lowers NDCG@5. Adding candidate-level graph records to history improves NDCG@5 by 2.28 points on Books and 2.54 on MovieTV; on these development queries, numerical counts outperform counts presented as text. A frozen evaluation on 274 previously unused Books users found that correct evidence assignment improved pairwise accuracy by 6.07 percentage points (95% CI [4.18, 8.00]). The abstract also reports that unrelated catalog text lowers Hit@1 from 44.77% to 38.70%, while 99.9% of rankings remain valid.

### Source excerpt

arXiv:2611.20837v1 Announce Type: cross Abstract: When several candidates have graph support, does it matter which candidate receives which supporter and path counts? We study how LLM rankers use collaborative evidence on Amazon Books and MovieTV. Swapping user-level evidence degrades ranking, while matched item substitutions have little effect. On fixed clean-trained checkpoints, unrelated catalog text lowers Hit@1 from 44.77% to 38.70%, with 99.9% of rankings still valid. Across all three paired seeds, the NDCG@5 difference between count and path prompts was larger after count training than after path training. Degree matching preserves target paths while giving more rivals support. Across the full degree-matched development pools, adding candidate-level graph records to history improves NDCG@5 by 2.28 points on Books and 2.54 on MovieTV. When the target and a rival both have support, path- and count-trained rankers benefit from retaining counts. On these development queries, adding counts numerically to history scores outperforms presenting them as text. For count-trained rankers, exchanging intact count pairs among supported candidates preserves support and token length, yet lowers NDCG@5 by 4.06 points on 141 Books queries and 3.26 on 104 MovieTV queries. A frozen evaluation on 274 previously unused Books users with supported targets and rivals confirms the attribution effect: correct assignment improves pairwise accuracy by 6.07 percentage points (95% CI [4.18, 8.00]).

## SERAG: SEmantical and Relational approach for Anomaly detection on knowledge Graphs

DevFeed: [SERAG: SEmantical and Relational approach for Anomaly detection on knowledge Graphs](<https://devfeed.tech/articles/serag-semantical-and-relational-approach-for-anomaly-detection-on-knowledge-graphs-138759.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18640>)

Author: Ludovic Moncla, Antoine Salazar, Yassir Lairgi, Khalid Benabdeslem, R\\'emy Cazabet

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [graph theory](<https://devfeed.tech/topics/graph-theory.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>)

Tags: [anomaly-detection](<https://devfeed.tech/tags/anomaly-detection.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>)

### AI overview

SERAG detects synthetic anomalies in knowledge graphs by fusing two plausibility scores: a semantic score from separately encoded subject, relation, and object labels, and a relational score from a relational graph convolutional network. The scores are standardized and calibrated before fusion. On a subset of ICEWS18 with vocabulary-constrained LLM-generated anomalies at 10% prevalence, SERAG achieved test AUPRCs of 0.321 with pooled splits and 0.258 with chronological splits, versus 0.159 and 0.146 for the strongest adapted baseline. Fusion improved mean test AUPRC over either branch, with a larger gain in the pooled protocol and a smaller validation-selected gain in the chronological protocol; additional anomaly supervision also improved performance. The evidence is limited to these synthetic anomalies and evaluated protocols.

### Source excerpt

arXiv:2611.18640v1 Announce Type: new Abstract: Knowledge graphs constructed from text can contain facts that are individually plausible yet inconsistent with their relational context. We introduce SERAG, a supervised anomaly detector that combines two complementary plausibility estimates: a semantic score computed from separately encoded subject, relation, and object labels, and a relational score obtained through a relational graph convolutional network. The scores are standardized, calibrated, and fused. We evaluate the method on a subset of ICEWS18 with vocabulary-constrained synthetic anomalies generated by an LLM, using pooled and chronological splits. At 10% anomaly prevalence, SERAG achieves test AUPRCs of 0.321 and 0.258, respectively, compared with 0.159 and 0.146 for the strongest adapted baseline. Fusion improves mean test AUPRC over either branch alone, with a larger gain in the pooled protocol and a smaller validation-selected gain in the chronological protocol. Additional anomaly supervision improves performance. These results support the complementarity of textual and relational signals for detecting synthetic anomalies under the evaluated protocols.

## Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents

DevFeed: [Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents](<https://devfeed.tech/articles/mining-workflow-graphs-for-black-box-boundary-testing-of-conversational-llm-agents-137927.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.06873>)

Author: Liting Lin, Boxi Yu, Yuzhong Zhang, Lionel Briand, David-Paul Niland, Emir Mu\\~noz

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [ablation](<https://devfeed.tech/tags/ablation.md>), [agents](<https://devfeed.tech/tags/agents.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [black-box](<https://devfeed.tech/tags/black-box.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [identity](<https://devfeed.tech/tags/identity.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [mining](<https://devfeed.tech/tags/mining.md>), [source-code](<https://devfeed.tech/tags/source-code.md>), [testing](<https://devfeed.tech/tags/testing.md>), [testing-framework](<https://devfeed.tech/tags/testing-framework.md>), [white-box](<https://devfeed.tech/tags/white-box.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

AgentEval tests conversational workflow boundaries without access to an agent's source code. It interacts with the agent to build a graph of activities and observed user actions, then generates tests at each node by replaying the path there before applying a perturbation. A separate LLM judge evaluates each test using only conversation turns. Across four τ³-bench agents, it covered an average of 38.8-46.0 distinct boundaries per agent over five repetitions. In ablations, tests that did not target graph nodes covered 2.0-7.0 fewer distinct boundaries for every agent and had higher duplicate rates for most.

### Source excerpt

arXiv:2607.06873v2 Announce Type: replace Abstract: Failures of conversational LLM agents can have real-world consequences, for example when an agent completes a transaction without the user's confirmation. An important class of such failures occurs at workflow boundaries, such as identity checks and confirmation steps, which a test can reach only after several turns of conversation. We present AgentEval, a black-box testing framework that discovers and tests these boundaries. AgentEval interacts with an agent to mine a conversational workflow graph, a model of its behavior whose nodes are the agent's activities and whose edges are the user actions observed between them. It generates tests at each node of this graph, replaying the conversational path to that node before applying a perturbation. AgentEval then runs each test, and a separate LLM judge decides whether it passes or fails using only the conversation turns. We benchmark AgentEval against a privileged, white-box auditor with access to the agent's underlying source code, which AgentEval never sees. On four $\tau^3$-bench agents, the boundary tests of AgentEval cover 38.8-46.0 distinct boundaries per agent on average over five repetitions. In ablation studies, generating tests without targeting the graph's nodes lowers the distinct-boundary count by 2.0-7.0 in every agent and raises the duplicate rate in most agents.

## eIRWR: Enhanced Iterative Random Walk with Restart for Scalable Root Cause Analysis in Microservices

DevFeed: [eIRWR: Enhanced Iterative Random Walk with Restart for Scalable Root Cause Analysis in Microservices](<https://devfeed.tech/articles/eirwr-enhanced-iterative-random-walk-with-restart-for-scalable-root-cause-analysis-in-microservices-136966.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.08073>)

Author: Saiful Khan, Afrah Farea

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [reliability-engineering](<https://devfeed.tech/topics/reliability-engineering.md>)

Tags: [alibaba](<https://devfeed.tech/tags/alibaba.md>), [cascade](<https://devfeed.tech/tags/cascade.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [cs-sy](<https://devfeed.tech/tags/cs-sy.md>), [dependency-graph](<https://devfeed.tech/tags/dependency-graph.md>), [eess-sy](<https://devfeed.tech/tags/eess-sy.md>), [loops](<https://devfeed.tech/tags/loops.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [mrr](<https://devfeed.tech/tags/mrr.md>), [online](<https://devfeed.tech/tags/online.md>), [random-walk](<https://devfeed.tech/tags/random-walk.md>), [root-cause-analysis](<https://devfeed.tech/tags/root-cause-analysis.md>)

### AI overview

eIRWR addresses a weakness in anomaly-based random walks: raw restart scores can favor highly anomalous downstream victims over the less anomalous root cause. The authors find that basic IRWR's resilience damping is equivalent to increasing the restart probability in Personalized PageRank (PPR), and use restart-tuned PPR as a fairer baseline. eIRWR additionally sharpens restart mass toward suspicious nodes and adds self-loops and backward edges to help probability accumulate at cascade sources. On three 12K-25K-node topologies from the Alibaba Microservice Trace Dataset, it reports the highest accuracy among compared graph-based methods at each tested root-cause visibility level. At visibility 0.3, MRR is 0.78; at high visibility, MRR is 0.95, with runtime under 30 ms on 17K-node graphs. These results are from the stated dataset and comparisons.

### Source excerpt

arXiv:2608.08073v2 Announce Type: replace Abstract: Root cause analysis (RCA) in microservice systems must find the faulty service behind symptoms that spread across hundreds or thousands of dependent services. Graph-based random walk methods propagate anomaly evidence over the service dependency graph. However, existing anomaly-restart walks restart from the raw anomaly vector, which is often dominated by strongly anomalous downstream victims rather than the less anomalous source. Through a controlled ablation of a basic anomaly-restart walk, the Iterative Random Walk with Restart (IRWR), we show that its ``resilience damping'' is equivalent to a higher restart probability in Personalized PageRank (PPR). Basic IRWR is therefore no stronger than a restart-tuned PPR, which we adopt as a fairer baseline. We then present Enhanced IRWR (eIRWR), which goes beyond restart tuning. It (a)~concentrates restart mass on the most suspicious nodes through power-law sharpening and (b)~adds self-loops and backward edges so that probability accumulates at cascade sources. On three large topologies (12K--25K nodes) from the Alibaba Microservice Trace Dataset, eIRWR is the most accurate of the compared graph-based methods at every level of root-cause visibility. At visibility $v = 0.3$, it reaches a Mean Reciprocal Rank (MRR) of $0.78$, about four times a restart-tuned PPR and nine times the best other baseline. At high visibility, it reaches MRR\,$= 0.95$ and runs in under 30\,ms on graphs with 17K nodes, so it is suitable for online use.

## Neo4j Virtual Graph is now generally available

DevFeed: [Neo4j Virtual Graph is now generally available](<https://devfeed.tech/articles/neo4j-virtual-graph-is-now-generally-available-135999.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/news/neo4j-virtual-graph-is-now-generally-available/>)

Author: Stu Moore

Published: 2026-11-16T17:25:06Z

Content type: release

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-workflows](<https://devfeed.tech/tags/agent-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [airport](<https://devfeed.tech/tags/airport.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [analyst](<https://devfeed.tech/tags/analyst.md>), [analysts](<https://devfeed.tech/tags/analysts.md>), [aura](<https://devfeed.tech/tags/aura.md>), [aura-graph-analytics](<https://devfeed.tech/tags/aura-graph-analytics.md>), [aws](<https://devfeed.tech/tags/aws.md>), [azure](<https://devfeed.tech/tags/azure.md>), [connected-data](<https://devfeed.tech/tags/connected-data.md>), [cypher-gql](<https://devfeed.tech/tags/cypher-gql.md>), [etl](<https://devfeed.tech/tags/etl.md>), [fraud-detection](<https://devfeed.tech/tags/fraud-detection.md>), [gcp](<https://devfeed.tech/tags/gcp.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [graph-technology](<https://devfeed.tech/tags/graph-technology.md>), [graph-visualization](<https://devfeed.tech/tags/graph-visualization.md>), [graphrag](<https://devfeed.tech/tags/graphrag.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [neo4j-aura](<https://devfeed.tech/tags/neo4j-aura.md>), [news](<https://devfeed.tech/tags/news.md>), [security](<https://devfeed.tech/tags/security.md>), [virtual-graph](<https://devfeed.tech/tags/virtual-graph.md>), [zero](<https://devfeed.tech/tags/zero.md>)

### AI overview

Neo4j Virtual Graph is generally available in Aura on GCP, with AWS and Azure support described as coming soon. It maps warehouse tables into a graph and translates Cypher queries into deterministic SQL executed in Snowflake, Databricks, Iceberg tables on S3, or BigQuery; data stays in the warehouse, and its access follows the connecting role's permissions and masking. Users can model graphs manually, from schema, or with AI, then query them through Neo4j tools and drivers. The excerpt highlights bounded quantified path patterns for traversals such as fraud and supply chain analysis, plus monitoring, pause/resume, and Private Link for dedicated environments. Virtual Graph is read-only and supports only part of Cypher; unsupported queries return error 42NG1. Warehouse execution means latency depends on compute and query complexity, with responses expected in seconds or minutes. The excerpt recommends AuraDB when writes, full Cypher, or millisecond response times are required. External IdPs, Aura MCP integration, and multi-source graphs are listed as forthcoming.

### Source excerpt

First on GCP, coming soon to AWS and Azure Today, Neo4j Virtual Graph is generally available in Neo4j Aura on GCP, with support for AWS and Azure to follow soon. Virtual Graph lets you build zero-ETL knowledge graphs, GraphRAG systems,... Read more ->

## PATTERN Can Be Solved from Memory: Testing Graph Neural Networks on Unseen Patterns

DevFeed: [PATTERN Can Be Solved from Memory: Testing Graph Neural Networks on Unseen Patterns](<https://devfeed.tech/articles/pattern-can-be-solved-from-memory-testing-graph-neural-networks-on-unseen-patterns-135729.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.15020>)

Author: Amin Najafgholizadeh, Mohsen Afsharchi

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [generalization in machine learning](<https://devfeed.tech/topics/generalization-in-machine-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cluster](<https://devfeed.tech/tags/cluster.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [generator](<https://devfeed.tech/tags/generator.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-neural-networks](<https://devfeed.tech/tags/graph-neural-networks.md>), [inference](<https://devfeed.tech/tags/inference.md>), [logistic-regression](<https://devfeed.tech/tags/logistic-regression.md>), [lookup](<https://devfeed.tech/tags/lookup.md>), [pattern](<https://devfeed.tech/tags/pattern.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [roc-auc](<https://devfeed.tech/tags/roc-auc.md>), [split](<https://devfeed.tech/tags/split.md>), [statistics](<https://devfeed.tech/tags/statistics.md>), [training](<https://devfeed.tech/tags/training.md>), [validation](<https://devfeed.tech/tags/validation.md>)

### AI overview

PATTERN's official split reuses 100 planted patterns across training and test graphs, allowing a lookup from training labels to reach 96.6% class-weighted accuracy without fitting a model; the same lookup scores 50.6% on unseen patterns, while a matcher using the generator reaches 99.2% on the official split. Of five retrained graph networks, GRASS and PPGT fall from the top two to the bottom two on unseen patterns, each losing 8.1 points even with pattern sizes matched. Logistic regression on two-hop node statistics exceeds all five networks' unseen-pattern runs. CKGConv's advantage follows the training pattern library and disappears when each training and validation graph gets a new pattern. The authors say the official split measures finding familiar patterns in new graphs and recommend reporting the same checkpoint's unseen-pattern score as well. They also report generator-based inference results on CLUSTER and Minesweeper, with the latter based on four of eight planned chains and none converging.

### Source excerpt

arXiv:2610.15020v2 Announce Type: replace Abstract: PATTERN asks graph neural networks to find a planted subgraph in a new host graph. The hosts change, but the benchmark draws just 100 patterns and reuses them across training and test splits. A lookup that extracts these patterns from the training labels achieves 96.6% class-weighted accuracy on the official test split, above every published result, without fitting a model or consulting the generator. On unseen patterns, the same lookup scores 50.6%. A matcher that also uses the generator reaches 99.2% on the official split. Among five graph networks we retrained, GRASS and PPGT go from the top two on the official split to the bottom two on unseen patterns. Each loses 8.1 percentage points even when familiar and unseen patterns are matched in size. Logistic regression on two-hop node statistics scores above every run of the five networks on unseen patterns. For CKGConv, the advantage follows the training patterns: it reappears with each of three independently drawn pattern libraries and disappears when every training and validation graph gets a new pattern. Generator-based inference also scores 82.3% on CLUSTER, compared with a published best of 81.6%. On Minesweeper's released board, four of eight planned chains produced samples within the time budget; none converged, but their pooled predictions reached 99.86% ROC AUC, above the published best of 99.55%. PATTERN's official split tests its intended task of finding familiar patterns in new graphs. We recommend reporting the same checkpoint's score on unseen patterns alongside it.

## A Practitioner's Guide to 6 Agentic GraphRAG Patterns

DevFeed: [A Practitioner's Guide to 6 Agentic GraphRAG Patterns](<https://devfeed.tech/articles/a-practitioner-s-guide-to-6-agentic-graphrag-patterns-134586.md>)

Original publisher: [Read original article](<https://towardsdatascience.com/a-practitioners-guide-to-6-agentic-graphrag-patterns/>)

Author: Partha Sarkar

Published: 2026-11-15T15:00:00Z

Content type: article

Language: en

Sources: [Towards Data Science](<https://devfeed.tech/sources/towards-data-science.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>)

Tags: [abstraction](<https://devfeed.tech/tags/abstraction.md>), [accelerated](<https://devfeed.tech/tags/accelerated.md>), [access-control](<https://devfeed.tech/tags/access-control.md>), [act](<https://devfeed.tech/tags/act.md>), [actions](<https://devfeed.tech/tags/actions.md>), [adaptive](<https://devfeed.tech/tags/adaptive.md>), [advanced](<https://devfeed.tech/tags/advanced.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-graphrag](<https://devfeed.tech/tags/agentic-graphrag.md>), [agents](<https://devfeed.tech/tags/agents.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-agents](<https://devfeed.tech/tags/autonomous-agents.md>), [context](<https://devfeed.tech/tags/context.md>), [context-graphs](<https://devfeed.tech/tags/context-graphs.md>), [graphrag](<https://devfeed.tech/tags/graphrag.md>), [guide](<https://devfeed.tech/tags/guide.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [llm](<https://devfeed.tech/tags/llm.md>), [operational](<https://devfeed.tech/tags/operational.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [practitioner](<https://devfeed.tech/tags/practitioner.md>), [rag](<https://devfeed.tech/tags/rag.md>), [user-intent](<https://devfeed.tech/tags/user-intent.md>)

### AI overview

The guide presents Agentic GraphRAG as a knowledge graph that agents navigate step by step and update with operational history, decisions, and user context. It outlines six patterns: operational memory for precedents and exceptions; execution memory for reusing successful tool paths and avoiding known failures; user context graphs for query-specific cross-session preferences; self-enriching topology graphs for incident matching, responder routing, and blast-radius analysis; hierarchical summaries for drilling from broad questions to atomic facts; and ReAct navigation for verified multi-hop retrieval. The proposed benefits include more relevant context, fewer repeated tool failures, and better grounded investigations. Trade-offs include schema and lifecycle governance, access controls, fresh incident and summary pipelines, and added latency and safeguards for iterative traversal. The article describes architectures and illustrative scenarios; it does not establish independent performance evidence for its quantified benefit claims.

### Source excerpt

How autonomous agents turn static knowledge graphs into living Context Graphs that remember decisions, user intent, and operational history The post A Practitioner's Guide to 6 Agentic GraphRAG Patterns appeared first on Towards Data Science.

## Nested Ensemble Learning with Topological Data Analysis for Graph Classification and Regression

DevFeed: [Nested Ensemble Learning with Topological Data Analysis for Graph Classification and Regression](<https://devfeed.tech/articles/nested-ensemble-learning-with-topological-data-analysis-for-graph-classification-and-regression-132931.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.14900>)

Author: Innocent Abaa, Umar Islambekov

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [Model Development](<https://devfeed.tech/topics/model-development.md>), [enhancing AI model accuracy](<https://devfeed.tech/topics/enhancing-ai-model-accuracy.md>)

Tags: [classification](<https://devfeed.tech/tags/classification.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [ensemble-learning](<https://devfeed.tech/tags/ensemble-learning.md>), [graph](<https://devfeed.tech/tags/graph.md>), [regression](<https://devfeed.tech/tags/regression.md>), [stat-ap](<https://devfeed.tech/tags/stat-ap.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>)

### AI overview

The framework combines graph topology from three centrality-based filters--closeness, betweenness, and degree2--through a three-level ensemble. It computes persistence diagrams for each filter, trains separate base models, combines their predictions into filter-specific ensembles, then integrates those ensembles for a final prediction. On simulated and real-world graph datasets, the authors report better classification accuracy and lower regression error than base models and standard stacking, and placement among the top three models across benchmarks. The supplied text does not include dataset details or quantitative results.

### Source excerpt

arXiv:2611.14900v1 Announce Type: cross Abstract: We propose a nested ensemble learning framework that utilizes Topological Data Analysis (TDA) to extract and integrate topological features from graph data, with the goal of improving performance on classification and regression tasks. Our approach computes persistence diagrams (PDs) using lower-star filtrations induced by three filter functions: closeness, betweenness, and degree2 centrality. To overcome the limitation of relying on a single filter, these PDs are integrated through a data-driven, three-level architecture. At Level-0, diverse base models are independently trained on the topological features extracted for each filter function. At Level-1, a meta-learner combines the predictions of these base models for each filter to form filter-specific ensembles. Finally, at Level-2, a meta-learner integrates the outputs of these filter-specific ensembles to produce the final prediction. We evaluate our method on both simulated and real-world graph datasets. Experimental results demonstrate that our framework consistently outperforms base models and standard stacking methods, achieving higher classification accuracy and lower regression error. It also surpasses existing state-of-the-art approaches, ranking among the top three models across all benchmarks.

## Common-Neighbor-Count-Based Representative Possible World Finding on Uncertain Graphs

DevFeed: [Common-Neighbor-Count-Based Representative Possible World Finding on Uncertain Graphs](<https://devfeed.tech/articles/common-neighbor-count-based-representative-possible-world-finding-on-uncertain-graphs-132677.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.23085>)

Author: Chengjie Gu, Xiaoliang Xu, Yuxiang Wang, Kai Yao, Mengzhao Wang, Tianxing Wu, Yingjie Xia, Xiangyu Ke

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [graph theory](<https://devfeed.tech/topics/graph-theory.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [graphs](<https://devfeed.tech/tags/graphs.md>)

### AI overview

The paper introduces CRPW, which selects a deterministic representative possible world to preserve expected common-neighbor counts between node pairs in an uncertain graph. This extends earlier representative-world approaches focused on per-node features, which may poorly estimate pair-based measures such as the Jaccard coefficient. The authors prove the selection problem is NP-hard and propose a two-stage algorithm that initializes and iteratively refines a graph. A counting-based estimate speeds refinement by checking whether an edge-state change helps, without calculating its exact benefit; a Beta-distribution-based stopping method aims to end refinement when the desired quality is reached. Experiments on five real-world uncertain graphs reportedly demonstrate effectiveness at preserving structural features.

### Source excerpt

arXiv:2607.23085v2 Announce Type: replace Abstract: Given an uncertain graph $\mathcal{G}$ with probabilistic edges, a representative possible world (RPW) is a deterministic graph that closely preserves the expected value of a designated basic structural feature in $\mathcal{G}$. As a proxy for $\mathcal{G}$, the RPW allows us to directly obtain approximate expectations of the higher-order features related to this preserved basic feature, thereby avoiding expensive enumeration or sampling on $\mathcal{G}$. Existing RPWs preserve per-node features such as degree and triangle degree but overlook common-neighbor counts between node pairs. As a result, they may poorly approximate the expected values of higher-order features that depend on these counts, e.g., Jaccard coefficient. Therefore, we study the \underline{C}ommon-neighbor-count-based \underline{R}epresentative \underline{P}ossible \underline{W}orld (CRPW) problem, extending RPWs from node features to node-pair features. Our problem seeks the possible world that best preserves the expected numbers of common neighbors between node pairs, and we prove that it is NP-hard. To address it, we develop a two-stage basic algorithm that quickly initializes a possible world and then refines it iteratively. We next accelerate the refinement with a counting-based estimation, as the refinement only requires determining whether an edge state change to the possible world is beneficial, rather than computing its exact magnitude. Furthermore, we design a Beta distribution-based adaptive termination method to automatically stop the refinement once the desired quality of the possible world is reached, preventing over- or under-execution. Extensive experiments on five real-world uncertain graphs demonstrate the effectiveness of our algorithms in preserving structural features.

## Online Test-Time Adaptation for Generalizable Dynamic Graph Anomaly Detection

DevFeed: [Online Test-Time Adaptation for Generalizable Dynamic Graph Anomaly Detection](<https://devfeed.tech/articles/online-test-time-adaptation-for-generalizable-dynamic-graph-anomaly-detection-132823.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.19858>)

Author: Jialun Zheng, Hanchen Yang, Jiannong Cao, Yankai Chen, Yuanjing Feng, Philip S. Yu

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [graph theory](<https://devfeed.tech/topics/graph-theory.md>)

Tags: [anomaly-detection](<https://devfeed.tech/tags/anomaly-detection.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [graph](<https://devfeed.tech/tags/graph.md>), [learning](<https://devfeed.tech/tags/learning.md>), [online](<https://devfeed.tech/tags/online.md>), [test](<https://devfeed.tech/tags/test.md>), [time](<https://devfeed.tech/tags/time.md>)

### AI overview

OTTA-DGAD adapts pretrained dynamic graph anomaly detectors to unseen domains as unlabeled target data arrive in sequential chunks, without requiring the full target dataset. It builds a memory of evolving normal and anomalous prototypes from temporal ego-graphs, retaining patterns shared across pretraining domains while incorporating target-domain patterns. Anomaly scores compare incoming edge representations with these prototypes. During test-then-adapt operation, confidence-based detection supplies pseudo-labels to update the memory, and relevant representations from prior chunks enrich each new chunk. The abstract reports state-of-the-art results across ten real-world datasets; it provides no numerical comparisons or further evaluation details.

### Source excerpt

arXiv:2608.19858v2 Announce Type: replace Abstract: Generalizable dynamic graph anomaly detection (DGAD) enables pretrained detectors to identify anomalies in unseen target domains without costly retraining. However, existing methods often fail for two reasons. First, they mainly rely on domain-agnostic patterns and miss domain-specific patterns that keep evolving. Second, they assume access to the full target domain data, whereas in more practical online test-time adaptation settings, target data arrive sequentially in unlabeled chunks. To address these limitations, we formulate online test-time adaptation for generalizable DGAD and propose OTTA-DGAD. OTTA-DGAD first extracts dynamic prototypes, i.e., evolving representations of normal and anomalous patterns, from temporal ego-graphs and stores them in a memory buffer. The buffer selectively retains general patterns shared across the source domains used for pretraining while incorporating new patterns from the target domain. An anomaly scorer then compares incoming edge representations against these prototypes to identify both general and domain-specific anomalies. During adaptation, OTTA-DGAD updates the memory buffer using reliable pseudo-labels identified through confidence-based detection. It further enriches each target chunk with relevant representations retained from previous chunks, compensating for information loss resulting from the sequential arrival of data. Extensive experiments under strict test-then-adapt OTTA settings demonstrate state-of-the-art performance on ten real-world datasets from diverse domains.

## Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMs

DevFeed: [Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMs](<https://devfeed.tech/articles/where-llm-annotators-fail-label-free-learning-on-graphs-with-llms-132795.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.27913>)

Author: Safal Thapaliya, Jiatan Huang, Chuxu Zhang

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [also](<https://devfeed.tech/tags/also.md>), [annotation](<https://devfeed.tech/tags/annotation.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [class](<https://devfeed.tech/tags/class.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cluster](<https://devfeed.tech/tags/cluster.md>), [clusters](<https://devfeed.tech/tags/clusters.md>), [code](<https://devfeed.tech/tags/code.md>), [conditional](<https://devfeed.tech/tags/conditional.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [fail](<https://devfeed.tech/tags/fail.md>), [free](<https://devfeed.tech/tags/free.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [learning](<https://devfeed.tech/tags/learning.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llms](<https://devfeed.tech/tags/llms.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

LLM-generated node labels can be unreliable in ways that vary across feature-space clusters, even within the same class. The paper proposes Cluster-Aware Noise Estimation (CANE), which estimates this cluster-specific reliability without ground-truth labels and uses it to select pseudo-labels to trust or correct. Across graph benchmarks and GNN backbones, the authors report improvements over the strongest label-free baselines, with larger gains on datasets showing stronger cluster-conditional noise.

### Source excerpt

arXiv:2605.27913v2 Announce Type: replace Abstract: Node classification on graphs often requires labeled nodes, yet obtaining labels at graph scale is expensive. When node attributes contain semantic content, such as paper abstracts, web pages, or product descriptions, large language models (LLMs) can provide low-cost supervision by annotating a small subset of nodes. However, these LLM-generated labels are noisy, and existing label-free graph learning methods usually treat this noise as either global or class-conditional. We find that LLM annotation errors are not only class-dependent but also region-dependent: within the same class, reliability can vary sharply across feature-space clusters. In light of this, we propose Cluster-Aware Noise Estimation (CANE), a label-free learning framework that estimates cluster-conditional LLM reliability without ground truth labels, and uses this estimate to decide which pseudo-labels to trust, and which labels to correct. Across various graph benchmarks and GNN backbones, CANE improves over the strongest label-free baselines, with the largest gains on datasets exhibiting stronger cluster-conditional noise. The code is available at https://github.com/thapaliya19/CANE.

## Git2KG: Mining socio-technical relationships in GitHub repositories as temporal knowledge graphs

DevFeed: [Git2KG: Mining socio-technical relationships in GitHub repositories as temporal knowledge graphs](<https://devfeed.tech/articles/git2kg-mining-socio-technical-relationships-in-github-repositories-as-temporal-knowledge-graphs-131715.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.15509>)

Author: Lennart Hessenauer, Lisi Qarkaxhija, Ingo Scholtes

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [GitHub](<https://devfeed.tech/topics/github.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [cs-se](<https://devfeed.tech/tags/cs-se.md>), [git](<https://devfeed.tech/tags/git.md>), [github](<https://devfeed.tech/tags/github.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [learning](<https://devfeed.tech/tags/learning.md>), [library](<https://devfeed.tech/tags/library.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mining](<https://devfeed.tech/tags/mining.md>), [ownership](<https://devfeed.tech/tags/ownership.md>), [python](<https://devfeed.tech/tags/python.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [relationships](<https://devfeed.tech/tags/relationships.md>), [repositories](<https://devfeed.tech/tags/repositories.md>), [snapshots](<https://devfeed.tech/tags/snapshots.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [time](<https://devfeed.tech/tags/time.md>), [visualization](<https://devfeed.tech/tags/visualization.md>)

### AI overview

Git2KG is a Python library for building temporal knowledge graphs from GitHub repositories. It extracts co-editing relationships and code ownership from Git logs, then disambiguates developer identities to connect those graphs with management and communication networks from issue trackers. It divides development events into fixed-size, non-overlapping time windows to produce repository snapshots, and supports computing node features and labels for machine learning. Snapshots can be exported to PyTorch Geometric, PathPyG, and NetworkX for temporal analysis, visualization, and graph learning. The abstract presents this as a way to combine data sources and retain collaboration dynamics that time-aggregated network analyses can miss.

### Source excerpt

arXiv:2611.15509v1 Announce Type: new Abstract: The widespread use of Git and GitHub in open source software (OSS) projects has produced large volumes of data on collaborative software development. Existing approaches to mine those data often use graph models to (i) capture communication between developers in the issue tracker, or (ii) represent developer-developer co-authorship or developer-file code ownership networks from the editing history of code artifacts. Integrating these data in a single knowledge graph (KG) is complicated by the need to disambiguate authors and match entities from multiple sources. Moreover, most works using network analysis have taken a time-aggregated perspective that neglects temporal dynamics of collaborations. To address these issues, we present Git2KG, an extensible Python library that mines temporal knowledge graphs (TKGs) from GitHub repositories. Git2KG extracts fine-grained co-editing relations and code ownership from the Git log. It further disambiguates developer identities to align the resulting graphs with management and communication networks extracted from GitHub issue trackers. Git2KG supports temporal analysis by slicing development events into fixed-size, non-overlapping time windows, yielding a series of knowledge graph snapshots per repository. It further supports computing node features and labels for downstream machine learning tasks. Snapshots can then be exported to PyTorch Geometric, PathPyG, and NetworkX for temporal network analysis, visualization, and graph learning.

## Diversity Curves for Graph Representation Learning

DevFeed: [Diversity Curves for Graph Representation Learning](<https://devfeed.tech/articles/diversity-curves-for-graph-representation-learning-128522.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.06466>)

Author: Katharina Limbeck, Nadja H\\"ausermann, Martin Carrasco, Guy Wolf, Bastian Rieck

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Graphs](<https://devfeed.tech/topics/graphs.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>)

Tags: [cluster](<https://devfeed.tech/tags/cluster.md>), [compare](<https://devfeed.tech/tags/compare.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [diversity](<https://devfeed.tech/tags/diversity.md>), [edge](<https://devfeed.tech/tags/edge.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [encoding](<https://devfeed.tech/tags/encoding.md>), [graph](<https://devfeed.tech/tags/graph.md>), [invariant](<https://devfeed.tech/tags/invariant.md>), [learning](<https://devfeed.tech/tags/learning.md>), [metric](<https://devfeed.tech/tags/metric.md>), [novel](<https://devfeed.tech/tags/novel.md>), [over](<https://devfeed.tech/tags/over.md>), [powerful](<https://devfeed.tech/tags/powerful.md>), [range](<https://devfeed.tech/tags/range.md>), [shapes](<https://devfeed.tech/tags/shapes.md>), [size](<https://devfeed.tech/tags/size.md>), [structure](<https://devfeed.tech/tags/structure.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

Diversity curves address the challenge of comparing graphs of different sizes by tracking structural diversity across edge-contraction coarsening levels. They encode the spread of graphs, described as an isometry invariant, in embeddings intended to be interpretable, efficient, and comparable across coarsening hierarchies. The authors state that edge contraction improves expressivity beyond structural descriptors alone. They report using the curves to cluster and visualize simulated graphs across sizes, distinguish single-cell graph geometry, compare molecular graph datasets, and characterize geometric shapes. The supplied text is an abstract and does not provide details of the experiments or comparative results.

### Source excerpt

arXiv:2605.06466v2 Announce Type: replace Abstract: Graph-level representations are crucial tools for characterising structural differences between graphs. However, comparing graphs with different cardinalities, even when sampled from the same underlying distribution, remains challenging. Unsupervised tasks in particular require interpretable, scalable, and reliable size-aware graph representations. Our work addresses these issues by tracking the structural diversity of a graph across coarsening levels. The resulting graph embeddings, which we denote diversity curves, are interpretable by construction, efficient, and directly comparable across coarsening hierarchies. Specifically, we track the spread of graphs, a novel isometry invariant that is inherently well-suited for encoding the metric diversity and geometry of graphs. We utilise edge contraction coarsening and prove that this improves expressivity, thus leading to more powerful graph-level representations than structural descriptors alone. Demonstrating their utility over a range of baseline methods in practice, we use diversity curves to (i) cluster and visualise simulated graphs across varying sizes, (ii) distinguish the geometry of single-cell graphs, (iii) compare the structure of molecular graph datasets, and (iv) characterise geometric shapes.

## Early Rug Pull Detection on Solana

DevFeed: [Early Rug Pull Detection on Solana](<https://devfeed.tech/articles/early-rug-pull-detection-on-solana-128899.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.13342>)

Author: Saba Heydaridoost, Kasra Kashani, Mohammad Mowlavi Sorond, Behnam Bahrak

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Solana](<https://devfeed.tech/topics/solana.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>)

Tags: [analytics](<https://devfeed.tech/tags/analytics.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [detection](<https://devfeed.tech/tags/detection.md>), [dex](<https://devfeed.tech/tags/dex.md>), [early-warning](<https://devfeed.tech/tags/early-warning.md>), [graph-neural-networks](<https://devfeed.tech/tags/graph-neural-networks.md>), [models](<https://devfeed.tech/tags/models.md>), [rpc](<https://devfeed.tech/tags/rpc.md>), [solana](<https://devfeed.tech/tags/solana.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [web3](<https://devfeed.tech/tags/web3.md>)

### AI overview

The study examines whether Solana token transfer graphs help detect rug pulls using only information available at prediction time. It samples 2,700 tokens from SolRPDS, combines one-minute Birdeye market histories with Solana RPC transfers, and defines a rug pull by liquidity drain, price collapse, and depletion persisting over a nominal 24 hours. It tests 12.5-, 35.5-, and 93-minute observation windows. In the earliest window, rug-pull and non-rug graphs differ in size, density, reciprocity, and receiver-side centralization. The design compares GNNs with matched non-graph models on identical samples and uses a fixed panel across all windows to separate the effect of longer observation from changes in token population. The supplied abstract does not report model performance or establish whether GNNs improve prediction.

### Source excerpt

arXiv:2611.13342v1 Announce Type: new Abstract: Web3 platforms that help users discover and trade newly launched crypto tokens, including launchpads, decentralized-exchange (DEX) interfaces, wallets, and token-analytics sites, must assess tokens before their legitimacy is clear. On Solana, where token creation is inexpensive and tokens use standard programs rather than custom per-token smart contracts, rug pulls can unfold within minutes. Effective warnings must therefore rely on limited histories. Although graph neural networks (GNNs) have improved rug-pull detection on EVM chains, it remains unclear whether transfer structure adds predictive value over non-graph models at minute-scale decision points, and how that value changes as history accumulates. We study 2,700 tokens sampled from SolRPDS, collecting one-minute market histories from Birdeye and token transfers from Solana RPC. We define a rug pull operationally by requiring a liquidity drain, price collapse, and persistent liquidity depletion over a nominal 24-hour period after token creation. All features use only information available at or before each prediction cutoff. We evaluate observation windows of 12.5, 35.5, and 93 minutes, selected in advance from the published lifespan distribution of Solana rug pulls, and represent each token as a temporal transfer graph. Within the first 12.5 minutes, rug-pull and non-rug graphs already differ in size, density, reciprocity, and receiver-side centralization. We compare GNNs against matched non-graph models using the same token-level and graph-summary features on identical samples. A fixed panel of tokens observed in all three windows further isolates the effect of longer observation from changes in token population. Our findings inform the design of early-warning mechanisms for newly launched Solana tokens in Web3 interfaces.

## Counting Hypertriangles through Hypergraph Orientations

DevFeed: [Counting Hypertriangles through Hypergraph Orientations](<https://devfeed.tech/articles/counting-hypertriangles-through-hypergraph-orientations-125657.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2601.03573>)

Author: Daniel Paul-Pena, Vaishali Surianarayanan, Deeparnab Chakrabarty, C. Seshadhri

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [graph theory](<https://devfeed.tech/topics/graph-theory.md>)

Tags: [algorithms](<https://devfeed.tech/tags/algorithms.md>), [computer-science](<https://devfeed.tech/tags/computer-science.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [cs-ds](<https://devfeed.tech/tags/cs-ds.md>), [cs-si](<https://devfeed.tech/tags/cs-si.md>), [data-structures-and-algorithms](<https://devfeed.tech/tags/data-structures-and-algorithms.md>), [experimental](<https://devfeed.tech/tags/experimental.md>)

### AI overview

The paper presents a framework for counting hypertriangles, defined as three pairwise-intersecting hyperedges, whose varied intersection patterns make them richer than ordinary graph triangles. Generalizing orientation and degeneracy ideas from graph algorithms, it develops provable counting algorithms and implements them in DITCH (Degeneracy Inspired Triangle Counter for Hypergraphs). Experiments report that DITCH is faster on all but one small instance, with speedups up to 100x, and uses 6-100x less memory than existing state-of-the-art methods.

### Source excerpt

arXiv:2601.03573v2 Announce Type: replace-cross Abstract: Counting the number of small patterns is a central task in network analysis. While this problem is well studied for graphs, many real-world datasets are naturally modeled as hypergraphs, motivating the need for efficient hypergraph motif counting algorithms. In particular, we study the problem of counting hypertriangles - collections of three pairwise-intersecting hyperedges. These hypergraph patterns have a rich structure with multiple distinct intersection patterns unlike graph triangles. Inspired by classical graph algorithms based on orientations and degeneracy, we develop a new theoretical framework that generalizes these concepts to hypergraphs and yields provable algorithms for hypertriangle counting. We implement these ideas in DITCH (Degeneracy Inspired Triangle Counter for Hypergraphs) and show experimentally that it is faster on all but one small instance, achieving speedups of up to 100x, and is 6-100x more memory-efficient than existing state-of-the-art methods.

## Scaling Graph Similarity Learning with Graph Neural Networks

DevFeed: [Scaling Graph Similarity Learning with Graph Neural Networks](<https://devfeed.tech/articles/scaling-graph-similarity-learning-with-graph-neural-networks-123457.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.09805>)

Author: Ahmet T\\"uzen, Helge Langseth, Kjetil N{\\o}rv{\\aa}g

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>)

Tags: [000](<https://devfeed.tech/tags/000.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [all](<https://devfeed.tech/tags/all.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [applications](<https://devfeed.tech/tags/applications.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [can](<https://devfeed.tech/tags/can.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-neural-networks](<https://devfeed.tech/tags/graph-neural-networks.md>), [learning](<https://devfeed.tech/tags/learning.md>), [networks](<https://devfeed.tech/tags/networks.md>), [neural](<https://devfeed.tech/tags/neural.md>), [neural-networks](<https://devfeed.tech/tags/neural-networks.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

FiLSim targets the scalability gap in GNN-based graph similarity learning, where exact Graph Edit Distance (GED) and Maximum Common Subgraph (MCS) computation is NP-hard and existing learned methods have focused mainly on smaller datasets. The framework uses a simplified GNN pipeline, evaluated on four benchmark datasets and four newly created large-scale datasets. To produce reliable GED labels at larger scales, the authors introduce a sequential graph-editing strategy. They report that FiLSim remains accurate on graphs exceeding 150,000 nodes, where baseline methods run out of memory or fail to learn, and scores all test pairs within seconds on a single GPU.

### Source excerpt

arXiv:2611.09805v1 Announce Type: new Abstract: Graph similarity computation is an important task in graph mining with many real-world applications, such as chemical compound analysis, program dependence comparison, and social network analysis. The problem is computationally challenging: Graph Edit Distance (GED) and Maximum Common Subgraph (MCS), which quantify the distance between graphs and identify their largest shared subgraph, respectively, are NP-hard to compute exactly. To address these computational challenges, Graph Neural Networks (GNNs) have been applied to this problem. However, existing GNN-based approaches have primarily focused on small-scale graph datasets, while scalability to larger scales remains underexplored. In this work, we propose FiLSim, a scalable GNN-based framework, and investigate whether a simplified GNN pipeline can maintain competitive performance on standard benchmarks while scaling to large graphs. We additionally propose a sequential graph-editing strategy to construct large-scale graph datasets with reliable GED labels to evaluate scalability. The proposed framework is evaluated on four benchmark datasets and four newly created large-scale datasets, demonstrating its effectiveness and scalability. FiLSim remains accurate on graphs with more than 150{,}000 nodes, where the baseline methods run out of memory or fail to learn, and scores all test pairs within seconds on a single GPU.

## GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks

DevFeed: [GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks](<https://devfeed.tech/articles/gabench-a-comprehensive-benchmark-for-evaluating-llm-agents-on-graph-analysis-tasks-124462.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.01684>)

Author: Jiarui Tan, Zhongjian Zhang, YaBo Guo, Jiawei Liu, Yujie Xing, Muhan Zhang, Cheng Yang, Chuan Shi

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [harvestbench](<https://devfeed.tech/topics/harvestbench.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Ground truth / benchmark quality](<https://devfeed.tech/topics/ground-truth-benchmark-quality.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-harnesses](<https://devfeed.tech/tags/agent-harnesses.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [also](<https://devfeed.tech/tags/also.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [building](<https://devfeed.tech/tags/building.md>), [call](<https://devfeed.tech/tags/call.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [graph](<https://devfeed.tech/tags/graph.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

GABench evaluates end-to-end LLM agent performance on graph analysis, addressing benchmarks that cover few graph types and tasks or provide graph information directly in prompts. It spans three graph types and four task categories--graph retrieval, graph theory, graph machine learning, and open-ended question answering--and supplies 84 executable tools. Its task generation pipeline produces 10,400 tasks with verifiable ground truth. Experiments report that agents struggle with complex tasks, harness choice significantly affects performance while current harnesses remain limited, and tool-call quality matters more than quantity.

### Source excerpt

arXiv:2608.01684v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly capable of planning, using tools, and interacting with external environments. They are typically supported by harnesses, which manage state and coordinate multi-step execution. Graph analysis provides a promising setting for evaluating their agentic capabilities, because it requires agents to access data and execute operations in a graph environment. However, existing graph benchmarks for LLMs provide limited coverage of graph tasks and graph types, making it difficult to comprehensively evaluate LLM agents. Moreover, they typically formulate graph analysis as text-based question answering, where graph information is directly provided in the prompt, limiting the evaluation of end-to-end agentic capabilities. To address these limitations, we introduce GABench, a comprehensive benchmark for agentic graph analysis. GABench spans three graph types and covers four graph analysis task categories: graph retrieval, graph theory, graph machine learning, and graph open-ended question answering. GABench also provides 84 executable tools for accessing graph data and performing diverse graph operations. Building on these tools, we develop an agentic graph analysis task generation pipeline and construct 10,400 tasks with verifiable ground truth.Using GABench, we evaluate a range of frontier LLMs and agent harnesses. Our experiments reveal three key findings: (1) Existing LLM agents still struggle with complex graph analysis tasks. (2) Harness choice significantly affects performance, yet existing harnesses remain limited on complex graph tasks. (3) Graph analysis depends more on tool-call quality than quantity. Our findings provide practical insights into the development and evaluation of LLM agents for graph analysis.

## Intention Driven Identification of In-Possession Match Phases in Association Football through Temporal Graph Learning

DevFeed: [Intention Driven Identification of In-Possession Match Phases in Association Football through Temporal Graph Learning](<https://devfeed.tech/articles/intention-driven-identification-of-in-possession-match-phases-in-association-football-through-temporal-graph-learning-123179.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.09289>)

Author: Yuesen Li, Daniel Link

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [attention](<https://devfeed.tech/tags/attention.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data-mining](<https://devfeed.tech/tags/data-mining.md>), [football](<https://devfeed.tech/tags/football.md>), [graph](<https://devfeed.tech/tags/graph.md>), [learning](<https://devfeed.tech/tags/learning.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [tracking](<https://devfeed.tech/tags/tracking.md>), [transformer](<https://devfeed.tech/tags/transformer.md>)

### AI overview

The proposed Temporal Graph Attention Network (T-GAN) segments continuous football possessions into six match phases under three tactical intentions, combining player interaction graphs, contextual features, and Transformer-based temporal modelling. Evaluated on seven Bundesliga matches with leave-one-match-out validation against rule-based, Random Forest, GNN, and Transformer baselines at frame and sequence levels, it reports that temporal modelling supports coherent segmentation and graph modelling adds value for transition phases such as Counter Attack. The evidence is limited to the supplied abstract; it gives no numerical performance results.

### Source excerpt

arXiv:2606.09289v4 Announce Type: replace Abstract: Recognising intentions from continuous movement trajectories is an important problem in spatiotemporal data mining. This becomes difficult when behaviours change over time and their boundaries cannot be directly observed. Football provides a useful setting for studying this problem because tactical intentions emerge from the coordinated movements of multiple players during possession. Existing methods for match phase recognition often classify individual frames, use predefined spatial rules, or identify only selected tactical patterns. They therefore cannot fully describe continuous possession sequences in which tactical intentions change over time. We address this gap by treating the identification of the in-possession match phase as a hierarchical sequence segmentation task. The framework includes three tactical intentions (Invade Opponent Space, Keep Possession, and Scoring) and six phases (Build Up, Progression, Counter Attack, Maintenance, Sustained Threat, and Finishing). We propose a Temporal Graph Attention Network (T-GAN) that combines player interaction graphs, contextual features, and Transformer based temporal modelling. The framework was evaluated on seven Bundesliga matches using leave-one-match-out validation and compared with rule-based, Random Forest, GNN, and Transformer baselines at both frame and sequence levels. The results show that temporal modelling is important for coherent phase segmentation, while graph modelling provides additional value for transition phases such as Counter Attack. The framework provides an interpretable method for discovering intention based behavioural segments from continuous player tracking data and supports automated tactical analysis in football.

## Towards Generalist Graph-Level Anomaly Detection

DevFeed: [Towards Generalist Graph-Level Anomaly Detection](<https://devfeed.tech/articles/towards-generalist-graph-level-anomaly-detection-120236.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.07706>)

Author: Junjun Pan, Yixin Liu, Yu Zheng, Fuyi Li, Alan Wee-Chung Liew, Shirui Pan

Published: 2026-11-06T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [Graphs](<https://devfeed.tech/topics/graphs.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>)

Tags: [anomaly-detection](<https://devfeed.tech/tags/anomaly-detection.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [generalist](<https://devfeed.tech/tags/generalist.md>), [graph](<https://devfeed.tech/tags/graph.md>)

### AI overview

GenGLAD targets graph-level anomaly detection across domains, where dataset-specific methods often require substantial in-domain data and training. It learns transferable anomaly patterns by extracting discriminative subgraphs with a graph neural network. At test time, it measures discrepancies between each extracted subgraph and multi-level context, then uses a lightweight scoring module to select informative signals for adaptation under limited supervision. The abstract reports strong performance, generalization, and data efficiency on diverse benchmarks compared with existing methods; it provides no specific datasets or quantitative results.

### Source excerpt

arXiv:2611.07706v1 Announce Type: new Abstract: Graph-level anomaly detection (GLAD) aims to identify graphs that deviate significantly from the majority. While recent advances have achieved competitive performance, existing approaches mainly follow a dataset-specific paradigm, requiring substantial in-domain data and training cost when applied to new application scenarios. This limits their scalability and practicality in real-world applications where labeled data is scarce and diverse domains are continuously emerging. In this paper, we investigate the problem of generalist GLAD, which seeks to learn a single unified model capable of detecting anomalous graphs across multiple domains with minimal supervision on the target data. This problem introduces key challenges, including learning transferable patterns from heterogeneous graph datasets and effective adaptation under limited supervision. To address these challenges, we propose GenGLAD, a generalist GLAD approach that leverages discriminative subgraph extraction as the core mechanism to learn transferable anomaly knowledge and enable efficient adaptation to new domains. Specifically, GenGLAD employs a graph neural network-based discriminative subgraph extraction model to learn the anomaly-discriminative substructures that distinguish anomalous and normal graphs across diverse domains. During the test-time adaptation phase, multi-dimensional discrepancies between the extracted subgraph and multi-level contextual information are calculated to characterize anomalies from multiple perspectives. For efficient adaptation, a lightweight scoring module is introduced to automatically decide the most informative signals, improving robustness against misleading patterns. Extensive experiments on diverse benchmark datasets demonstrate that the proposed approach achieves strong performance, superior generalization ability, and improved data efficiency compared to existing methods.

## Explainable Anomaly Detection in 5G Networks through Continuous Time Graphs

DevFeed: [Explainable Anomaly Detection in 5G Networks through Continuous Time Graphs](<https://devfeed.tech/articles/explainable-anomaly-detection-in-5g-networks-through-continuous-time-graphs-118705.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.06225>)

Author: Thomas Hoger (LAAS, LAAS-SARA, LAAS-RISC), Philippe Owezarski (LAAS, LAAS-SARA, LAAS-RISC)

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>), [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [network security](<https://devfeed.tech/topics/network-security.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [network-intelligence](<https://devfeed.tech/topics/network-intelligence.md>)

Tags: [5g](<https://devfeed.tech/tags/5g.md>), [anomaly-detection](<https://devfeed.tech/tags/anomaly-detection.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-ne](<https://devfeed.tech/tags/cs-ne.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [detection](<https://devfeed.tech/tags/detection.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [networks](<https://devfeed.tech/tags/networks.md>)

### AI overview

The paper models 5G network exchanges as a dynamic graph and applies graph-based learning to detect anomalies. The representation is intended to capture packet-level semantic content alongside sequential and topological context, which the authors say can help identify sophisticated, multi-stage attacks. They evaluate the approach using popular dynamic graph models; the supplied excerpt reports potential for 5G anomaly detection but gives no model names or performance results.

### Source excerpt

arXiv:2611.06225v1 Announce Type: new Abstract: 5G networks increasingly resemble distributed systems in their design. It then becomes crucial to move beyond traditional network-based detection methods and to explore alternative approaches. In this work, we propose a formalization of 5G network exchanges as a dynamic graph, on which we apply techniques from the field of graph-based learning to detect anomalies effectively. This representation allows for fine-grained analysis of packet-level semantic content, while simultaneously capturing sequential and topological contexts, both of which are essential for identifying sophisticated and multi-stage attacks. To assess the effectiveness of this formalism, we evaluate it with the most popular dynamic graph models, demonstrating its potential for 5G anomaly detection.

## GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?

DevFeed: [GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?](<https://devfeed.tech/articles/graphip-bench-how-hard-is-it-to-steal-a-graph-neural-network-and-can-we-stop-it-118218.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.12827>)

Author: Kaixiang Zhao, Bolin Shen, Yuyang Dai, Shayok Chakraborty, Yushun Dong

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [attack](<https://devfeed.tech/tags/attack.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [behaviour](<https://devfeed.tech/tags/behaviour.md>), [bench](<https://devfeed.tech/tags/bench.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [black](<https://devfeed.tech/tags/black.md>), [box](<https://devfeed.tech/tags/box.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [change](<https://devfeed.tech/tags/change.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [graph](<https://devfeed.tech/tags/graph.md>), [it](<https://devfeed.tech/tags/it.md>), [network](<https://devfeed.tech/tags/network.md>), [neural](<https://devfeed.tech/tags/neural.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [stop](<https://devfeed.tech/tags/stop.md>)

### AI overview

GraphIP-Bench evaluates GNN extraction attacks and ownership defenses under one black-box protocol, using shared splits, queries, and budgets. It combines 12 extraction attacks, 12 defenses across watermarking, output perturbation, and query-pattern detection, 10 public graphs, three GNN backbones, and three tasks; it measures fidelity, task utility, ownership verification, and computational cost. A joint track tests whether defenses retain watermark verification on extracted surrogates. The abstract reports that GNNs are easy to steal at medium query budgets and most defenses do not change this. Several watermarks verify on protected models but lose much of their signal on surrogates. Heterophilic graphs are harder to steal, and cross-architecture mismatch reduces but does not prevent extraction. The benchmark includes reproducible scripts and configurations and is integrated into PyGIP.

### Source excerpt

arXiv:2605.12827v3 Announce Type: replace-cross Abstract: Graph neural networks (GNNs) deployed as cloud services can be *stolen* through *model-extraction attacks*, which train a surrogate from query responses to reproduce the target's behaviour, and a growing line of ownership defenses tries to prevent or trace such theft. The title of this paper asks two questions: *how hard is it to steal a GNN?*, and *can we stop it?* Prior work cannot answer either, because experiments use inconsistent datasets, threat models, and metrics. We introduce *GraphIP-Bench*, a unified benchmark which evaluates both sides under a single black-box protocol. It integrates twelve extraction attacks, twelve defenses spanning watermarking, output-perturbation, and query-pattern-detection families, ten public graphs covering homophilic, heterophilic, and large-scale regimes, three GNN backbones, and three graph-learning tasks, and it reports fidelity, task utility, ownership verification, and computational cost on shared splits, queries, and budgets. We further add a joint attack-and-defense track which runs every attack on every defended target and measures watermark verification on the resulting surrogate, which exposes the protection that a defense retains after extraction. The empirical picture is short: stealing a GNN is easy at medium query budgets and most defenses do not change this; several watermarks verify reliably on the protected model but lose most of their verification signal on the extracted surrogate, which exposes a gap that single-model evaluations miss; and heterophilic graphs are systematically harder to steal, while a cross-architecture mismatch between target and surrogate reduces but does not prevent extraction. We release *GraphIP-Bench* with reproducible scripts and configurations, and integrate the attacks and defenses into the PyGIP library.

[Next page](<https://devfeed.tech/topics/graph-mining.md?cursor=WyIyMDI2LTExLTA1VDA1OjAwOjAwKzAwOjAwIiwgIjVjZjZjODc2LTBmZGQtNDZhZC1hMGNlLTNkMDMzZTkxNzdlNCJd>)