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

Factorized Explainer for Graph Neural Networks (2312.05596v2)

Published 9 Dec 2023 in cs.LG

Abstract: Graph Neural Networks (GNNs) have received increasing attention due to their ability to learn from graph-structured data. To open the black-box of these deep learning models, post-hoc instance-level explanation methods have been proposed to understand GNN predictions. These methods seek to discover substructures that explain the prediction behavior of a trained GNN. In this paper, we show analytically that for a large class of explanation tasks, conventional approaches, which are based on the principle of graph information bottleneck (GIB), admit trivial solutions that do not align with the notion of explainability. Instead, we argue that a modified GIB principle may be used to avoid the aforementioned trivial solutions. We further introduce a novel factorized explanation model with theoretical performance guarantees. The modified GIB is used to analyze the structural properties of the proposed factorized explainer. We conduct extensive experiments on both synthetic and real-world datasets to validate the effectiveness of our proposed factorized explainer.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. Concrete autoencoders for differentiable feature selection and reconstruction. arXiv preprint arXiv:1901.09346.
  2. Global explainability of gnns via logic combination of learned concepts. In Proceedings of the International Conference on Learning Representations (ICLR).
  3. Improving graph neural network expressivity via subgraph isomorphism counting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1): 657–668.
  4. Utilizing Molecular Network Information via Graph Convolutional Neural Networks to Predict Metastatic Event in Breast Cancer. Studies in health technology and informatics, 267: 181–186.
  5. 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.
  6. Lecture notes on network information theory.
  7. Graph Neural Networks for Social Recommendation. The World Wide Web Conference.
  8. Cooperative Explanations of Graph Neural Networks. In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, 616–624.
  9. DEGREE: Decomposition Based Explanation for Graph Neural Networks. In International Conference on Learning Representations.
  10. Graph random neural networks for semi-supervised learning on graphs. Advances in neural information processing systems, 33: 22092–22103.
  11. Inductive representation learning on large graphs. In NIPS, 1024–1034.
  12. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations.
  13. Feature selection: A data perspective. ACM computing surveys (CSUR), 50(6): 1–45.
  14. Generative causal explanations for graph neural networks. In International Conference on Machine Learning, 6666–6679. PMLR.
  15. Federated social recommendation with graph neural network. ACM Transactions on Intelligent Systems and Technology (TIST), 13(4): 1–24.
  16. Graph Sequence Neural Network with an Attention Mechanism for Traffic Speed Prediction. ACM Transactions on Intelligent Systems and Technology (TIST), 13(2): 1–24.
  17. Parameterized explainer for graph neural network. Advances in neural information processing systems, 33: 19620–19631.
  18. CLEAR: Generative Counterfactual Explanations on Graphs.
  19. Molecular Geometry Prediction using a Deep Generative Graph Neural Network. Scientific Reports, 9.
  20. Interpretable and generalizable graph learning via stochastic attention mechanism. In International Conference on Machine Learning, 15524–15543. PMLR.
  21. Interpretable Geometric Deep Learning via Learnable Randomness Injection. In Proceedings of the International Conference on Learning Representations (ICLR).
  22. E (n) equivariant graph neural networks. In International conference on machine learning, 9323–9332. PMLR.
  23. Reinforcement Learning Enhanced Explainer for Graph Neural Networks. Advances in Neural Information Processing Systems, 34.
  24. Deep learning and the information bottleneck principle. In 2015 ieee information theory workshop (itw), 1–5. IEEE.
  25. Graph Attention Networks. In International Conference on Learning Representations.
  26. Empower Post-hoc Graph Explanations with Information Bottleneck: A Pre-training and Fine-tuning Perspective. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2349–2360.
  27. GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networks. In Proceedings of the International Conference on Learning Representations (ICLR).
  28. Towards multi-grained explainability for graph neural networks. Advances in Neural Information Processing Systems, 34: 18446–18458.
  29. Graph information bottleneck. Advances in Neural Information Processing Systems, 33: 20437–20448.
  30. Relevant Walk Search for Explaining Graph Neural Networks. In ICML.
  31. How Powerful are Graph Neural Networks? In International Conference on Learning Representations.
  32. Counterfactual Learning on Heterogeneous Graphs with Greedy Perturbation. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’23, 2988–2998. New York, NY, USA: Association for Computing Machinery. ISBN 9798400701030.
  33. Graph convolutional neural networks for web-scale recommender systems. In KDD, 974–983.
  34. Gnnexplainer: Generating explanations for graph neural networks. In NeurIPS, 9240–9251.
  35. Graph Information Bottleneck for Subgraph Recognition. In International Conference on Learning Representations.
  36. Xgnn: Towards model-level explanations of graph neural networks. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 430–438.
  37. Explainability in graph neural networks: A taxonomic survey. IEEE Transactions on Pattern Analysis and Machine Intelligence.
  38. On explainability of graph neural networks via subgraph explorations. In International Conference on Machine Learning, 12241–12252. PMLR.
  39. MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentation. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 3286–3296.
  40. Link prediction based on graph neural networks. Advances in neural information processing systems, 31.
  41. Gstarx: Explaining graph neural networks with structure-aware cooperative games. Advances in Neural Information Processing Systems, 35: 19810–19823.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Rundong Huang (4 papers)
  2. Farhad Shirani (45 papers)
  3. Dongsheng Luo (46 papers)
Citations (6)
View on Semantic Scholar

Summary

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

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