Papers
Topics
Authors
Recent
Search
2000 character limit reached

Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networks

Published 2 Jul 2024 in cs.LG and cs.AI | (2407.01979v1)

Abstract: Graph Neural Networks (GNNs) have emerged as a prominent framework for graph mining, leading to significant advances across various domains. Stemmed from the node-wise representations of GNNs, existing explanation studies have embraced the subgraph-specific viewpoint that attributes the decision results to the salient features and local structures of nodes. However, graph-level tasks necessitate long-range dependencies and global interactions for advanced GNNs, deviating significantly from subgraph-specific explanations. To bridge this gap, this paper proposes a novel intrinsically interpretable scheme for graph classification, termed as Global Interactive Pattern (GIP) learning, which introduces learnable global interactive patterns to explicitly interpret decisions. GIP first tackles the complexity of interpretation by clustering numerous nodes using a constrained graph clustering module. Then, it matches the coarsened global interactive instance with a batch of self-interpretable graph prototypes, thereby facilitating a transparent graph-level reasoning process. Extensive experiments conducted on both synthetic and real-world benchmarks demonstrate that the proposed GIP yields significantly superior interpretability and competitive performance to~the state-of-the-art counterparts. Our code will be made publicly available.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (73)
  1. Molecular generative graph neural networks for drug discovery. Neurocomputing 450 (2021), 242–252.
  2. Fast computation of graph kernels. In Annual Conference on Neural Information Processing Systems.
  3. Karsten M Borgwardt and Hans-Peter Kriegel. 2005. Shortest-path kernels on graphs. In IEEE International Conference on Data Mining.
  4. Grarep: Learning graph representations with global structural information. In ACM International Conference on Information and Knowledge Management.
  5. Deep neural networks for learning graph representations. In AAAI Conference on Artificial Intelligence.
  6. Gated residual recurrent graph neural networks for traffic prediction. In AAAI Conference on Artificial Intelligence.
  7. This looks like that: deep learning for interpretable image recognition.
  8. Structure-aware transformer for graph representation learning. In International Conference on Machine Learning.
  9. Distribution-aware graph representation learning for transient stability assessment of power system. In International Joint Conference on Neural Networks.
  10. Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization. In ACM Knowledge Discovery and Data Mining.
  11. Powerformer: A Section-adaptive Transformer for Power Flow Adjustment. arXiv preprint arXiv:2401.02771 (2024).
  12. Distribution knowledge embedding for graph pooling. IEEE Transactions on Knowledge and Data Engineering (2022).
  13. FINC: An Efficient and Effective Optimization Method for Normalized Cut. IEEE Trans on Pattern Analysis and Machine Intelligence (2022).
  14. Enyan Dai and Suhang Wang. 2021. Towards self-explainable graph neural network. In ACM International Conference on Information and Knowledge Management.
  15. Enyan Dai and Suhang Wang. 2022. Towards prototype-based self-explainable graph neural network. arXiv preprint arXiv:2210.01974 (2022).
  16. Eliciting structural and semantic global knowledge in unsupervised graph contrastive learning. In AAAI Conference on Artificial Intelligence.
  17. Paul D Dobson and Andrew J Doig. 2003. Distinguishing enzyme structures from non-enzymes without alignments. Journal of molecular biology 330, 4 (2003), 771–783.
  18. Deep MinCut: Learning Node Embeddings by Detecting Communities. Pattern Recognition 134 (2023), 109126.
  19. Kergnns: Interpretable graph neural networks with graph kernels. In Proceedings of the AAAI Conference on Artificial Intelligence.
  20. Scalable kernels for graphs with continuous attributes. In Annual Conference on Neural Information Processing Systems.
  21. On graph kernels: Hardness results and efficient alternatives. In Learning Theory and Kernel Machines: 16th Annual Conference on Learning Theory and 7th Kernel Workshop, COLT/Kernel 2003, Washington, DC, USA, August 24-27, 2003. Proceedings. 129–143.
  22. Neural message passing for quantum chemistry. In International Conference on Machine Learning.
  23. Inductive Representation Learning on Large Graphs. Annual Conference on Neural Information Processing Systems.
  24. ASGN: An active semi-supervised graph neural network for molecular property prediction. In ACM Knowledge Discovery and Data Mining.
  25. Learning graph neural networks for image style transfer. In ECCV.
  26. Amalgamating knowledge from heterogeneous graph neural networks. In CVPR.
  27. Deep Graph Reprogramming. In CVPR.
  28. Marginalized kernels between labeled graphs. In International Conference on Machine Learning.
  29. Thomas N Kipf and Max Welling. 2016. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations.
  30. Janet L Kolodner. 1992. An introduction to case-based reasoning. Artificial intelligence review 6, 1 (1992), 3–34.
  31. GOAT: A global transformer on large-scale graphs. In International Conference on Machine Learning.
  32. Learnable structural semantic readout for graph classification. In IEEE International Conference on Data Mining.
  33. A survey of explainable graph neural networks: Taxonomy and evaluation metrics. arXiv preprint arXiv:2207.12599 (2022).
  34. Transmission interface power flow adjustment: A deep reinforcement learning approach based on multi-task attribution map. IEEE Transactions on Power Systems (2023).
  35. On Calibration of Graph Neural Networks for Node Classification. In International Joint Conference on Neural Networks.
  36. Federated social recommendation with graph neural network. ACM Transactions on Intelligent Systems and Technology 13, 4 (2022), 1–24.
  37. Parameterized explainer for graph neural network. In Annual Conference on Neural Information Processing Systems.
  38. Interpretable and generalizable graph learning via stochastic attention mechanism. In International Conference on Machine Learning.
  39. Interpretable and steerable sequence learning via prototypes. In ACM Knowledge Discovery and Data Mining.
  40. Giannis Nikolentzos and Michalis Vazirgiannis. 2020. Random walk graph neural networks. In Annual Conference on Neural Information Processing Systems.
  41. Explainability methods for graph convolutional neural networks. In IEEE Conference on Computer Vision and Pattern Recognition.
  42. Recipe for a general, powerful, scalable graph transformer. In Annual Conference on Neural Information Processing Systems.
  43. Tight continuous relaxation of the balanced k-cut problem. In Annual Conference on Neural Information Processing Systems.
  44. Self-supervised graph transformer on large-scale molecular data. In Annual Conference on Neural Information Processing Systems.
  45. Peter J Rousseeuw. 1987. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of computational and applied mathematics 20 (1987), 53–65.
  46. Bernhard Schölkopf. 2000. The kernel trick for distances. In Annual Conference on Neural Information Processing Systems.
  47. Shi. 2003. Multiclass spectral clustering. In International Conference on Computer Vision.
  48. Jianbo Shi and Jitendra Malik. 2000. Normalized cuts and image segmentation. IEEE Trans on Pattern Analysis and Machine Intelligence 22, 8 (2000), 888–905.
  49. Mastering the game of go without human knowledge. nature 550, 7676 (2017), 354–359.
  50. Predicting protein function from structure: unique structural features of proteases. Proceedings of the National Academy of Sciences 97, 8 (2000), 3954–3958.
  51. Causal attention for interpretable and generalizable graph classification. In ACM Knowledge Discovery and Data Mining.
  52. Graph Attention Networks. In International Conference on Learning Representations.
  53. Minh Vu and My T Thai. 2020. Pgm-explainer: Probabilistic graphical model explanations for graph neural networks. In Annual Conference on Neural Information Processing Systems.
  54. Multi-similarity loss with general pair weighting for deep metric learning. In IEEE Conference on Computer Vision and Pattern Recognition.
  55. Adversarial erasing with pruned elements: Towards better graph lottery ticket. In European Conference on Artificial Intelligence.
  56. Dynamic graph cnn for learning on point clouds. ACM Transactions on Graphics (2019).
  57. Spatiotemporal-Augmented Graph Neural Networks for Human Mobility Simulation. IEEE Transactions on Knowledge and Data Engineering (2024).
  58. Graph information bottleneck. In Annual Conference on Neural Information Processing Systems.
  59. Representing long-range context for graph neural networks with global attention. In Annual Conference on Neural Information Processing Systems.
  60. MoleculeNet: a benchmark for molecular machine learning. Chemical science 9, 2 (2018), 513–530.
  61. Pinar Yanardag and SVN Vishwanathan. 2015. Deep graph kernels. In ACM Knowledge Discovery and Data Mining.
  62. Trajgat: A graph-based long-term dependency modeling approach for trajectory similarity computation. In ACM Knowledge Discovery and Data Mining.
  63. Train Once and Explain Everywhere: Pre-training Interpretable Graph Neural Networks. In Annual Conference on Neural Information Processing Systems.
  64. Graph convolutional neural networks for web-scale recommender systems. In ACM Knowledge Discovery and Data Mining.
  65. Gnnexplainer: Generating explanations for graph neural networks. In Annual Conference on Neural Information Processing Systems.
  66. Hierarchical graph representation learning with differentiable pooling. In Annual Conference on Neural Information Processing Systems.
  67. Graph Information Bottleneck for Subgraph Recognition. In International Conference on Learning Representations.
  68. Xgnn: Towards model-level explanations of graph neural networks. In ACM Knowledge Discovery and Data Mining.
  69. On explainability of graph neural networks via subgraph explorations. In International Conference on Machine Learning.
  70. Traffic flow forecasting with spatial-temporal graph diffusion network. In AAAI Conference on Artificial Intelligence.
  71. Protgnn: Towards self-explaining graph neural networks. In AAAI Conference on Artificial Intelligence.
  72. Graphsmote: Imbalanced node classification on graphs with graph neural networks. In ACM International Conference on Web Search And Data Mining.
  73. Transition propagation graph neural networks for temporal networks. IEEE Transactions on Neural Networks and Learning Systems (2022).
Citations (2)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up