# Community detection in complex networks via node similarity, graph representation learning, and hierarchical clustering

DevFeed: [Community detection in complex networks via node similarity, graph representation learning, and hierarchical clustering](<https://devfeed.tech/articles/community-detection-in-complex-networks-via-node-similarity-graph-representation-learning-and-hierarchical-clustering-116620.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2303.12212>)

Author: {\\L}ukasz Brzozowski, Grzegorz Siudem, Marek Gagolewski

Published: 2026-11-04T05:00:00Z

Content type: article

Language: en

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

Topics: [clustering](<https://devfeed.tech/topics/clustering.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Deep learning](<https://devfeed.tech/topics/deep-learning.md>)

Tags: [clustering](<https://devfeed.tech/tags/clustering.md>), [community-detection](<https://devfeed.tech/tags/community-detection.md>), [complex](<https://devfeed.tech/tags/complex.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-si](<https://devfeed.tech/tags/cs-si.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [graph](<https://devfeed.tech/tags/graph.md>), [networks](<https://devfeed.tech/tags/networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [time-complexity](<https://devfeed.tech/tags/time-complexity.md>)

## AI overview

The paper proposes three hierarchical frameworks for community detection, combining linkage-based clustering with vertex proximity measures or graph representation learning. Across 364 combinations tested on Stochastic Block Model graphs and real datasets, the strongest pipelines--using Wasserman-Faust or mutual information-based PPMI proximity, and DNGR representations--perform competitively with Leiden and Louvain while producing compatible nested partitions at every possible cardinality. The authors report near-zero practical cost to partition quality for this flexibility and greater accuracy on graphs with many small communities. Their main limitation is computational complexity: on personal machines, the approach is confined to networks of roughly 10,000 vertices.

## Source excerpt

arXiv:2303.12212v3 Announce Type: replace-cross Abstract: Community detection is a significant challenge in analysing real graphs, including social, citation, biological, and many other networks. This article proposes three new, general, hierarchical frameworks to deal with this task. The introduced approach supports various linkage-based clustering algorithms, vertex proximity matrices, and graph representation learning models. We compare 364 module combinations on Stochastic Block Model graphs and real-life datasets. We observe that our best pipelines (Wasserman-Faust and the mutual information-based PPMI proximity, as well as the deep learning-based DNGR representations) perform competitively with the state-of-the-art Leiden and Louvain algorithms. At the same time, unlike the latter, they remain hierarchical. Thus, they output a series of nested partitions of all possible cardinalities which are compatible with each other. This feature is crucial when the number of correct partitions is unknown in advance, and we show that it is obtained at near-zero practical cost in terms of partition quality. On graphs composed of many small communities, our pipelines are more accurate than the reference solutions. Nevertheless, the downside of our approach is its time complexity, which confines the framework to networks of some 10000 vertices on personal machines.