Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time (2405.01762v2)

Published 2 May 2024 in cs.LG

Abstract: Understanding and explaining the predictions of Graph Neural Networks (GNNs), is crucial for enhancing their safety and trustworthiness. Subgraph-level explanations are gaining attention for their intuitive appeal. However, most existing subgraph-level explainers face efficiency challenges in explaining GNNs due to complex search processes. The key challenge is to find a balance between intuitiveness and efficiency while ensuring transparency. Additionally, these explainers usually induce subgraphs by nodes, which may introduce less-intuitive disconnected nodes in the subgraph-level explanations or omit many important subgraph structures. In this paper, we reveal that inducing subgraph explanations by edges is more comprehensive than other subgraph inducing techniques. We also emphasize the need of determining the subgraph explanation size for each data instance, as different data instances may involve different important substructures. Building upon these considerations, we introduce a training-free approach, named EiG-Search. We employ an efficient linear-time search algorithm over the edge-induced subgraphs, where the edges are ranked by an enhanced gradient-based importance. We conduct extensive experiments on a total of seven datasets, demonstrating its superior performance and efficiency both quantitatively and qualitatively over the leading baselines.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. Robust counterfactual explanations on graph neural networks. Advances in Neural Information Processing Systems, 34:5644–5655, 2021.
  2. Explainability techniques for graph convolutional networks. In ICML 2019 Workshop” Learning and Reasoning with Graph-Structured Representations”, 2019.
  3. Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. correlation with molecular orbital energies and hydrophobicity. Journal of medicinal chemistry, 34(2):786–797, 1991.
  4. When comparing to ground truth is wrong: On evaluating gnn explanation methods. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’21, pp.  332–341, New York, NY, USA, 2021. Association for Computing Machinery. ISBN 9781450383325. doi: 10.1145/3447548.3467283.
  5. DEGREE: Decomposition based explanation for graph neural networks. In International Conference on Learning Representations, 2022.
  6. Graphlime: Local interpretable model explanations for graph neural networks. IEEE Transactions on Knowledge and Data Engineering, 2022.
  7. Factorized explainer for graph neural networks. arXiv preprint arXiv:2312.05596, 2024.
  8. Derivation and validation of toxicophores for mutagenicity prediction. Journal of medicinal chemistry, 48(1):312–320, 2005.
  9. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations, 2017.
  10. DAG matters! GFlownets enhanced explainer for graph neural networks. In The Eleventh International Conference on Learning Representations, 2023.
  11. Generative causal explanations for graph neural networks. In International Conference on Machine Learning, pp.  6666–6679. PMLR, 2021.
  12. GOAt: Explaining graph neural networks via graph output attribution. In The Twelfth International Conference on Learning Representations, 2024. URL https://openreview.net/forum?id=2Q8TZWAHv4.
  13. Parameterized explainer for graph neural network. Advances in neural information processing systems, 33:19620–19631, 2020.
  14. Distill n’explain: explaining graph neural networks using simple surrogates. In International Conference on Artificial Intelligence and Statistics, pp.  6199–6214. PMLR, 2023.
  15. Explainability methods for graph convolutional neural networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  10772–10781, 2019.
  16. Interpreting graph neural networks for nlp with differentiable edge masking. In International Conference on Learning Representations, 2021.
  17. Higher-order explanations of graph neural networks via relevant walks. IEEE transactions on pattern analysis and machine intelligence, 44(11):7581–7596, 2021.
  18. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision, pp.  618–626, 2017.
  19. Reinforcement learning enhanced explainer for graph neural networks. Advances in Neural Information Processing Systems, 34:22523–22533, 2021.
  20. Learning important features through propagating activation differences. In International conference on machine learning, pp.  3145–3153. PMLR, 2017.
  21. Axiomatic attribution for deep networks. In International conference on machine learning, pp.  3319–3328. PMLR, 2017.
  22. Pgm-explainer: Probabilistic graphical model explanations for graph neural networks. Advances in neural information processing systems, 33:12225–12235, 2020.
  23. Comparison of descriptor spaces for chemical compound retrieval and classification. In Sixth International Conference on Data Mining (ICDM’06), pp.  678–689. IEEE Computer Society, 2006.
  24. Graph Neural Networks: Foundations, Frontiers, and Applications. Springer Singapore, Singapore, 2022.
  25. How powerful are graph neural networks? In International Conference on Learning Representations, 2019.
  26. SAME: Uncovering GNN black box with structure-aware shapley-based multipiece explanations. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  27. Gnnexplainer: Generating explanations for graph neural networks. Advances in neural information processing systems, 32, 2019.
  28. Motifexplainer: a motif-based graph neural network explainer. arXiv preprint arXiv:2202.00519, 2022.
  29. On explainability of graph neural networks via subgraph explorations. In International Conference on Machine Learning, pp.  12241–12252. PMLR, 2021.
  30. Explainability in graph neural networks: A taxonomic survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, pp.  1–19, 2022. ISSN 1939-3539. doi: 10.1109/tpami.2022.3204236.
  31. Gstarx: Explaining graph neural networks with structure-aware cooperative games. Advances in Neural Information Processing Systems, 35:19810–19823, 2022.
  32. Relex: A model-agnostic relational model explainer. In Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society, pp.  1042–1049, 2021.
  33. Towards faithful and consistent explanations for graph neural networks. In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, pp.  634–642, 2023.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets