# DGPExplainer: Generating Prototype Sequence Explanations for Dynamic Graph Neural Networks

DevFeed: [DGPExplainer: Generating Prototype Sequence Explanations for Dynamic Graph Neural Networks](<https://devfeed.tech/articles/dgpexplainer-generating-prototype-sequence-explanations-for-dynamic-graph-neural-networks-132968.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.15224>)

Author: Jinlong Hu, Shixu Fan, Chongzhang Li

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

Content type: article

Language: en

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

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

Tags: [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [explainer](<https://devfeed.tech/tags/explainer.md>), [graph-neural-networks](<https://devfeed.tech/tags/graph-neural-networks.md>), [prototype](<https://devfeed.tech/tags/prototype.md>), [sequence](<https://devfeed.tech/tags/sequence.md>), [temporal](<https://devfeed.tech/tags/temporal.md>)

## AI overview

DGPExplainer is a post-hoc explainer for dynamic graph neural networks (DGNNs), designed to produce class-specific explanations as sequences of graph patterns. It applies local explanation methods to identify important elements in temporal snapshots, decomposes each time step into prototypes, then learns and generates prototype sequences from those symbolic representations. The authors report experiments on synthetic and real-world datasets that produce prototype-based explanations across multiple classes. The supplied text is an abstract and does not provide details on evaluation metrics, baselines, or limitations.

## Source excerpt

arXiv:2611.15224v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have been successfully applied to learning from graph-structured data. However, applying them to dynamic graphs-where nodes and edges evolve over time-presents significant challenges, particularly regarding explainability. While explanation techniques for static GNNs are well established, they do not readily extend to dynamic GNNs (DGNNs) due to the added complexity introduced by temporal dynamics and spatiotemporal dependencies, especially when generating model-level explanations. To address this gap, we introduce DGPExplainer, a post-hoc, prototype-based explainer specifically designed for DGNN models that transforms their complex decision-making processes into human-understandable, analogical, case-based explanations. DGPExplainer first employs local explanation methods to identify important elements within temporal snapshots of dynamic graph sequences. It then decomposes the graph at each time step into distinct prototypes, thereby symbolizing the dynamic graph sequence. Finally, we design a sequence generation method that uses these symbolized sequences to learn and generate class-specific dynamic graph pattern sequences that serve as prototype explanations. Experiments on both synthetic and real-world datasets demonstrate that our method effectively produces prototype-based explanations for DGNN models across multiple classes.