Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck
Pages 2572 - 2583
Abstract
Temporal Graph Neural Networks (TGNN) have the ability to capture both the graph topology and dynamic dependencies of interactions within a graph over time. There has been a growing need to explain the predictions of TGNN models due to the difficulty in identifying how past events influence their predictions. Since the explanation model for a static graph cannot be readily applied to temporal graphs due to its inability to capture temporal dependencies, recent studies proposed explanation models for temporal graphs. However, existing explanation models for temporal graphs rely on post-hoc explanations, requiring separate models for prediction and explanation, which is limited in two aspects: efficiency and accuracy of explanation. In this work, we propose a novel built-in explanation framework for temporal graphs, called Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck (TGIB). TGIB provides explanations for event occurrences by introducing stochasticity in each temporal event based on the Information Bottleneck theory. Experimental results demonstrate the superiority of TGIB in terms of both the link prediction performance and explainability compared to state-of-the-art methods. This is the first work that simultaneously performs prediction and explanation for temporal graphs in an end-to-end manner. The source code of TGIB is available at https://github.com/sang-woo-seo/TGIB.
Supplemental Material
MP4 File - 1478-video
This video is a brief promotional video for "Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck" to be presented at KDD 2024. It analyzes the issues with existing explanation models for temporal graphs and introduces how our model addresses these problems.
- Download
- 16.47 MB
References
[1]
Alexander A Alemi, Ian Fischer, Joshua V Dillon, and Kevin Murphy. 2016. Deep variational information bottleneck. arXiv preprint arXiv:1612.00410 (2016).
[2]
Julia Amann, Alessandro Blasimme, Effy Vayena, Dietmar Frey, Vince I Madai, and Precise4Q Consortium. 2020. Explainability for artificial intelligence in healthcare: a multidisciplinary perspective. BMC medical informatics and decision making, Vol. 20 (2020), 1--9.
[3]
Weilin Cong, Si Zhang, Jian Kang, Baichuan Yuan, Hao Wu, Xin Zhou, Hanghang Tong, and Mehrdad Mahdavi. 2023. Do We Really Need Complicated Model Architectures For Temporal Networks? arXiv preprint arXiv:2302.11636 (2023).
[4]
Hanjun Dai, Yichen Wang, Rakshit Trivedi, and Le Song. 2016. Deep coevolutionary network: Embedding user and item features for recommendation. arXiv preprint arXiv:1609.03675 (2016).
[5]
Finale Doshi-Velez and Been Kim. 2017. Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608 (2017).
[6]
Valeria Gelardi, Didier Le Bail, Alain Barrat, and Nicolas Claidiere. 2021. From temporal network data to the dynamics of social relationships. Proceedings of the Royal Society B, Vol. 288, 1959 (2021), 20211164.
[7]
Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, and Alexander Lerchner. 2016. beta-vae: Learning basic visual concepts with a constrained variational framework. In International conference on learning representations.
[8]
Shenyang Huang, Yasmeen Hitti, Guillaume Rabusseau, and Reihaneh Rabbany. 2020. Laplacian change point detection for dynamic graphs. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 349--358.
[9]
Eric Jang, Shixiang Gu, and Ben Poole. 2017. Categorical reparameterization with gumbel-softmax. In International Conference on Learning Representations.
[10]
Thomas N Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations.
[11]
Srijan Kumar, Xikun Zhang, and Jure Leskovec. 2019. Predicting dynamic embedding trajectory in temporal interaction networks. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. 1269--1278.
[12]
Namkyeong Lee, Dongmin Hyun, Gyoung S Na, Sungwon Kim, Junseok Lee, and Chanyoung Park. 2023. Conditional Graph Information Bottleneck for Molecular Relational Learning. arXiv preprint arXiv:2305.01520 (2023).
[13]
Namkyeong Lee, Kanghoon Yoon, Gyoung S Na, Sein Kim, and Chanyoung Park. 2023. Shift-robust molecular relational learning with causal substructure. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1200--1212.
[14]
Shuang Li, Mingquan Feng, Lu Wang, Abdelmajid Essofi, Yufeng Cao, Junchi Yan, and Le Song. 2021. Explaining point processes by learning interpretable temporal logic rules. In International Conference on Learning Representations.
[15]
Zhao Li, Pengrui Hui, Peng Zhang, Jiaming Huang, Biao Wang, Ling Tian, Ji Zhang, Jianliang Gao, and Xing Tang. 2021. What happens behind the scene? Towards fraud community detection in e-commerce from online to offline. In Companion Proceedings of the Web Conference 2021. 105--113.
[16]
Dongsheng Luo, Wei Cheng, Dongkuan Xu, Wenchao Yu, Bo Zong, Haifeng Chen, and Xiang Zhang. 2020. Parameterized explainer for graph neural network. Advances in neural information processing systems, Vol. 33 (2020), 19620--19631.
[17]
Siqi Miao, Mia Liu, and Pan Li. 2022. Interpretable and generalizable graph learning via stochastic attention mechanism. In International Conference on Machine Learning. PMLR, 15524--15543.
[18]
Pietro Panzarasa, Tore Opsahl, and Kathleen M Carley. 2009. Patterns and dynamics of users' behavior and interaction: Network analysis of an online community. Journal of the American Society for Information Science and Technology, Vol. 60, 5 (2009), 911--932.
[19]
Xue Bin Peng, Angjoo Kanazawa, Sam Toyer, Pieter Abbeel, and Sergey Levine. 2018. Variational discriminator bottleneck: Improving imitation learning, inverse rl, and gans by constraining information flow. arXiv preprint arXiv:1810.00821 (2018).
[20]
James W Pennebaker, Martha E Francis, and Roger J Booth. 2001. Linguistic inquiry and word count: LIWC 2001. Mahway: Lawrence Erlbaum Associates, Vol. 71, 2001 (2001), 2001.
[21]
Fabíola SF Pereira, Jo ao Gama, Sandra de Amo, and Gina MB Oliveira. 2018. On analyzing user preference dynamics with temporal social networks. Machine Learning, Vol. 107 (2018), 1745--1773.
[22]
Phillip E Pope, Soheil Kolouri, Mohammad Rostami, Charles E Martin, and Heiko Hoffmann. 2019. Explainability methods for graph convolutional neural networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 10772--10781.
[23]
Ismini Psychoula, Andreas Gutmann, Pradip Mainali, Sharon H Lee, Paul Dunphy, and Fabien Petitcolas. 2021. Explainable machine learning for fraud detection. Computer, Vol. 54, 10 (2021), 49--59.
[24]
Emanuele Rossi, Ben Chamberlain, Fabrizio Frasca, Davide Eynard, Federico Monti, and Michael Bronstein. 2020. Temporal graph networks for deep learning on dynamic graphs. arXiv preprint arXiv:2006.10637 (2020).
[25]
Sangwoo Seo, Sungwon Kim, and Chanyoung Park. 2023. Interpretable Prototype-based Graph Information Bottleneck. arXiv preprint arXiv:2310.19906 (2023).
[26]
Claude Elwood Shannon. 1948. A mathematical theory of communication. The Bell system technical journal, Vol. 27, 3 (1948), 379--423.
[27]
Jitesh Shetty and Jafar Adibi. [n.,d.]. The Enron Email Dataset Database Schema and Brief Statistical Report (2004). Available on http://www. isi. edu/ adibi/Enron/Enron_Dataset_Report. pdf ( [n.,d.]).
[28]
David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton, Yutian Chen, Timothy Lillicrap, Fan Hui, Laurent Sifre, George van den Driessche, Thore Graepel, and Demis Hassabis. 2017. Mastering the game of Go without human knowledge. Nature, Vol. 550 (2017). http://dx.doi.org/10.1038/nature24270
[29]
Duygu Sinanc, Umut Demirezen, cSeref Saugirouglu, et al. 2021. Explainable credit card fraud detection with image conversion. (2021).
[30]
Jiabin Tang, Lianghao Xia, and Chao Huang. 2023. Explainable Spatio-Temporal Graph Neural Networks. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 2432--2441.
[31]
Naftali Tishby, Fernando C Pereira, and William Bialek. 2000. The information bottleneck method. arXiv preprint physics/0004057 (2000).
[32]
Rakshit Trivedi, Mehrdad Farajtabar, Prasenjeet Biswal, and Hongyuan Zha. 2019. Dyrep: Learning representations over dynamic graphs. In International conference on learning representations.
[33]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017).
[34]
Petar Velivcković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph attention networks. International Conference on Learning Representations (2018).
[35]
Minh Vu and My T Thai. 2020. Pgm-explainer: Probabilistic graphical model explanations for graph neural networks. Advances in neural information processing systems, Vol. 33 (2020), 12225--12235.
[36]
Lu Wang, Xiaofu Chang, Shuang Li, Yunfei Chu, Hui Li, Wei Zhang, Xiaofeng He, Le Song, Jingren Zhou, and Hongxia Yang. 2021. Tcl: Transformer-based dynamic graph modelling via contrastive learning. arXiv preprint arXiv:2105.07944 (2021).
[37]
Yanbang Wang, Yen-Yu Chang, Yunyu Liu, Jure Leskovec, and Pan Li. 2021. Inductive representation learning in temporal networks via causal anonymous walks. arXiv preprint arXiv:2101.05974 (2021).
[38]
Tailin Wu, Hongyu Ren, Pan Li, and Jure Leskovec. 2020. Graph information bottleneck. Advances in Neural Information Processing Systems, Vol. 33 (2020), 20437--20448.
[39]
Wenwen Xia, Mincai Lai, Caihua Shan, Yao Zhang, Xinnan Dai, Xiang Li, and Dongsheng Li. 2022. Explaining temporal graph models through an explorer-navigator framework. In The Eleventh International Conference on Learning Representations.
[40]
Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, and Kannan Achan. 2020. Inductive representation learning on temporal graphs. arXiv preprint arXiv:2002.07962 (2020).
[41]
Zhitao Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, and Jure Leskovec. 2019. Gnnexplainer: Generating explanations for graph neural networks. Advances in neural information processing systems, Vol. 32 (2019).
[42]
Jiaxuan You, Tianyu Du, and Jure Leskovec. 2022. ROLAND: graph learning framework for dynamic graphs. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2358--2366.
[43]
Junchi Yu, Jie Cao, and Ran He. 2022. Improving subgraph recognition with variational graph information bottleneck. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 19396--19405.
[44]
Junchi Yu, Tingyang Xu, Yu Rong, Yatao Bian, Junzhou Huang, and Ran He. 2020. Graph information bottleneck for subgraph recognition. arXiv preprint arXiv:2010.05563 (2020).
[45]
Zaixi Zhang, Qi Liu, Hao Wang, Chengqiang Lu, and Cheekong Lee. 2022. Protgnn: Towards self-explaining graph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 9127--9135.
Index Terms
- Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck
Index terms have been assigned to the content through auto-classification.
Recommendations
Explainable Spatio-Temporal Graph Neural Networks
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementSpatio-temporal graph neural networks (STGNNs) have gained popularity as a powerful tool for effectively modeling spatio-temporal dependencies in diverse real-world urban applications, including intelligent transportation and public safety. However, the ...
Distributed temporal graph analytics with GRADOOP
AbstractTemporal property graphs are graphs whose structure and properties change over time. Temporal graph datasets tend to be large due to stored historical information, asking for scalable analysis capabilities. We give a complete overview of Gradoop, ...
Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment
Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over recent years. Instance-level GNN explanation aims to discover critical input elements, such as nodes or edges, that the target GNN relies upon ...
Comments
Information & Contributors
Information
Published In
August 2024
6901 pages
Copyright © 2024 Owner/Author.
This work is licensed under a Creative Commons Attribution International 4.0 License.
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 24 August 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT)
- Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT)
- National Research Foundation of Korea(NRF) funded by Ministry of Science and ICT
Conference
KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
August 25 - 29, 2024
Barcelona, Spain
Acceptance Rates
Overall Acceptance Rate 1,133 of 8,635 submissions, 13%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 229Total Downloads
- Downloads (Last 12 months)229
- Downloads (Last 6 weeks)101
Reflects downloads up to 10 Nov 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in