Task-agnostic graph explanations
AUTHORs: 
Yaochen Xie, Sumeet Katariya, 
Xianfeng Tang, Edward Huang, Nikhil Rao, Karthik Subbian, Shuiwang JiAuthors Info & Claims
Yaochen Xie, Sumeet Katariya, Xianfeng Tang, Edward Huang, Nikhil Rao, Karthik Subbian, Shuiwang JiAuthors Info & ClaimsArticle No.: 874, Pages 12027 - 12039
Abstract
Graph Neural Networks (GNNs) have emerged as powerful tools to encode graph-structured data. Due to their broad applications, there is an increasing need to develop tools to explain how GNNs make decisions given graph-structured data. Existing learning-based GNN explanation approaches are task-specific in training and hence suffer from crucial drawbacks. Specifically, they are incapable of producing explanations for a multitask prediction model with a single explainer. They are also unable to provide explanations in cases where the GNN is trained in a self-supervised manner, and the resulting representations are used in future downstream tasks. To address these limitations, we propose a Task-Agnostic GNN Explainer (TAGE) that is independent of downstream models and trained under self-supervision with no knowledge of downstream tasks. TAGE enables the explanation of GNN embedding models with unseen downstream tasks and allows efficient explanation of multitask models. Our extensive experiments show that TAGE can significantly speed up the explanation efficiency by using the same model to explain predictions for multiple downstream tasks while achieving explanation quality as good as or even better than current state-of-the-art GNN explanation approaches. Our code is publicly available as part of the DIG library.
Supplementary Material
Supplemental material.
- Download
- 724.76 KB
References
[1]
Wenqi Fan, Yao Ma, Qing Li, Yuan He, Eric Zhao, Jiliang Tang, and Dawei Yin. Graph neural networks for social recommendation. In The World Wide Web Conference, pages 417-426, 2019.
[2]
Matthias Fey and Jan E. Lenssen. Fast graph representation learning with PyTorch Geometric. In ICLR Workshop on Representation Learning on Graphs and Manifolds, 2019.
[3]
Justin Gilmer, Samuel S Schoenholz, Patrick F Riley, Oriol Vinyals, and George E Dahl. Neural message passing for quantum chemistry. In Proceedings of the 34th International Conference on Machine Learning, pages 1263-1272. PMLR, 2017.
[4]
Michael Gutmann and Aapo Hyvärinen. Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pages 297-304, 2010.
[5]
R Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Phil Bachman, Adam Trischler, and Yoshua Bengio. Learning deep representations by mutual information estimation and maximization. In International Conference on Learning Representations, 2019.
[6]
Weihua Hu, Bowen Liu, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay Pande, and Jure Leskovec. Strategies for pre-training graph neural networks. In International Conference on Learning Representations, 2020.
[7]
Dandan Huang, Yonglan Liu, Bozhi Shi, Yueting Li, Guixue Wang, and Guizhao Liang. Comprehensive 3D-QSAR and binding mode of BACE-1 inhibitors using R-group search and molecular docking. Journal of Molecular Graphics and Modelling, 45:65-83, 2013.
[8]
Priti Jain and Hemant R. Jadhav. Quantitative structure activity relationship analysis of aminoimidazoles as bace-i inhibitors. Medicinal Chemistry Research, 22(4):1740-1746, 2013.
[9]
Wengong Jin, Regina Barzilay, and Tommi Jaakkola. Multi-objective molecule generation using interpretable substructures. In Proceedings of the 37th International Conference on Machine Learning, pages 4849-4859. PMLR, 2020.
[10]
Thomas N Kipf and Max Welling. Variational graph auto-encoders. arXiv preprint arXiv:1611.07308, 2016.
[11]
Thomas N. Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations, 2017.
[12]
Wanyu Lin, Hao Lan, and Baochun Li. Generative causal explanations for graph neural networks. In Proceedings of the 38th International Conference on Machine Learning, 2021.
[13]
Wanyu Lin, Hao Lan, Hao Wang, and Baochun Li. Orphicx: A causality-inspired latent variable model for interpreting graph neural networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13729-13738, 2022.
[14]
Meng Liu, Youzhi Luo, Limei Wang, Yaochen Xie, Hao Yuan, Shurui Gui, Haiyang Yu, Zhao Xu, Jingtun Zhang, Yi Liu, Keqiang Yan, Haoran Liu, Cong Fu, Bora M Oztekin, Xuan Zhang, and Shuiwang Ji. DIG: A turnkey library for diving into graph deep learning research. Journal of Machine Learning Research, 22(240):1-9, 2021.
[15]
Dongsheng Luo, Wei Cheng, Dongkuan Xu, Wenchao Yu, Bo Zong, Haifeng Chen, and Xiang Zhang. Parameterized explainer for graph neural network. In Advances in Neural Information Processing Systems, pages 19620-19631, 2020.
[16]
Youzhi Luo, Keqiang Yan, and Shuiwang Ji. GraphDF: A discrete flow model for molecular graph generation. In Proceedings of the 38th International Conference on Machine Learning, pages 7192-7203. PMLR, 2021.
[17]
Siqi Miao, Mia Liu, and Pan Li. Interpretable and generalizable graph learning via stochastic attention mechanism. In Proceedings of the 39th International Conference on Machine Learning, pages 15524-15543. PMLR, 2022.
[18]
Sebastian Nowozin, Botond Cseke, and Ryota Tomioka. f-GAN: Training generative neural samplers using variational divergence minimization. In Advances in Neural Information Processing Systems, pages 271-279, 2016.
[19]
Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. PyTorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems, pages 8024-8035. 2019.
[20]
Phillip E Pope, Soheil Kolouri, Mohammad Rostami, Charles E Martin, and Heiko Hoffmann. Explainability methods for graph convolutional neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 10772-10781, 2019.
[21]
Avanti Shrikumar, Peyton Greenside, and Anshul Kundaje. Learning important features through propagating activation differences. In Proceedings of the 34th International Conference on Machine Learning, pages 3145-3153, 2017.
[22]
Teague Sterling and John J Irwin. ZINC 15 - Ligand discovery for everyone. Journal of Chemical Information and Modeling, 55(11):2324-2337, 2015.
[23]
Fan-Yun Sun, Jordan Hoffman, Vikas Verma, and Jian Tang. Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization. In International Conference on Learning Representations, 2019.
[24]
Petar Veličković, William Fedus, William L. Hamilton, Pietro Liò, Yoshua Bengio, and Devon Hjelm. Deep graph infomax. In International Conference on Learning Representations, 2019.
[25]
Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. Graph attention networks. In International Conference on Learning Representations, 2018.
[26]
Limei Wang, Yi Liu, Yuchao Lin, Haoran Liu, and Shuiwang Ji. ComENet: Towards complete and efficient message passing for 3D molecular graphs. In Advances in Neural Information Processing Systems, 2022.
[27]
Xiang Wang, Yingxin Wu, An Zhang, Xiangnan He, and Tat-Seng Chua. Towards multi-grained explainability for graph neural networks. In Advances in Neural Information Processing Systems, pages 18446-18458, 2021.
[28]
Zhengyang Wang, Meng Liu, Youzhi Luo, Zhao Xu, Yaochen Xie, Limei Wang, Lei Cai, Qi Qi, Zhuoning Yuan, Tianbao Yang, and Shuiwang Ji. Advanced graph and sequence neural networks for molecular property prediction and drug discovery. Bioinformatics, 38(9):2579-2586, 2022.
[29]
Zhenqin Wu, Bharath Ramsundar, Evan N Feinberg, Joseph Gomes, Caleb Geniesse, Aneesh S Pappu, Karl Leswing, and Vijay Pande. MoleculeNet: A benchmark for molecular machine learning. Chemical Science, 9(2):513-530, 2018.
[30]
Yaochen Xie, Zhao Xu, and Shuiwang Ji. Self-supervised representation learning via latent graph prediction. In Proceedings of the 39th International Conference on Machine Learning, pages 24460-24477. PMLR, 2022.
[31]
Yaochen Xie, Zhao Xu, Jingtun Zhang, Zhengyang Wang, and Shuiwang Ji. Self-supervised learning of graph neural networks: A unified review. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.
[32]
Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. How powerful are graph neural networks? In International Conference on Learning Representations, 2019.
[33]
Rex Ying, Ruining He, Kaifeng Chen, Pong Eksombatchai, William L Hamilton, and Jure Leskovec. Graph convolutional neural networks for web-scale recommender systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 974-983, 2018.
[34]
Zhitao Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, and Jure Leskovec. GNNEx-plainer: Generating explanations for graph neural networks. In Advances in Neural Information Processing Systems, pages 9244-9255, 2019.
[35]
Haiyang Yu, Limei Wang, Bokun Wang, Meng Liu, Tianbao Yang, and Shuiwang Ji. GraphFM: Improving large-scale GNN training via feature momentum. In Proceedings of the 39th International Conference on Machine Learning, pages 25684-25701. PMLR, 2022.
[36]
Hao Yuan, Haiyang Yu, Jie Wang, Kang Li, and Shuiwang Ji. On explainability of graph neural networks via subgraph explorations. In International Conference on Machine Learning, pages 12241-12252. PMLR, 2021.
[37]
Hao Yuan, Haiyang Yu, Shurui Gui, and Shuiwang Ji. Explainability in graph neural networks: A taxonomic survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.
[38]
Yanqiao Zhu, Yichen Xu, Feng Yu, Qiang Liu, Shu Wu, and Liang Wang. Deep graph contrastive representation learning. In ICML Workshop on Graph Representation Learning and Beyond, 2020.
[39]
Marinka Zitnik and Jure Leskovec. Predicting multicellular function through multi-layer tissue networks. Bioinformatics, 33(14):i190-i198, 2017.
Index Terms
- Task-agnostic graph explanations
Index terms have been assigned to the content through auto-classification.
Recommendations
Model-Agnostic Counterfactual Explanations of Recommendations
UMAP '21: Proceedings of the 29th ACM Conference on User Modeling, Adaptation and PersonalizationExplanations for algorithmically generated recommendations is an important requirement for transparent and trustworthy recommender systems. When the internal recommendation model is not inherently interpretable (e.g., most contemporary systems are ...
Learning Model-Agnostic Counterfactual Explanations for Tabular Data
WWW '20: Proceedings of The Web Conference 2020Counterfactual explanations can be obtained by identifying the smallest change made to an input vector to influence a prediction in a positive way from a user’s viewpoint; for example, from ’loan rejected’ to ’awarded’ or from ’high risk of ...
Complexity results for explanations in the structural-model approach
We analyze the computational complexity of Halpern and Pearl's (causal) explanations in the structural-model approach, which are based on their notions of weak and actual cause. In particular, we give a precise picture of the complexity of deciding ...
Comments
Information & Contributors
Information
Published In
November 2022
39114 pages
ISBN:9781713871088
- Editors:
- S. Koyejo,
- S. Mohamed,
- A. Agarwal,
- D. Belgrave,
- K. Cho,
- A. Oh
Copyright © 2022 Neural Information Processing Systems Foundation, Inc.
Publisher
Curran Associates Inc.
Red Hook, NY, United States
Publication History
Published: 03 April 2024
Qualifiers
- Research-article
- Research
- Refereed limited
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 12 Jan 2025