Just Accepted
Efficient GNN Explanation via Learning Removal-based Attribution
Authors: 
Yao Rong, Guanchu Wang, Qizhang Feng, Ninghao Liu, Zirui Liu, Enkelejda Kasneci, Xia HuAuthors Info & Claims
Yao Rong, Guanchu Wang, Qizhang Feng, Ninghao Liu, Zirui Liu, Enkelejda Kasneci, Xia HuAuthors Info & ClaimsAccepted on 25 July 2024
Abstract
As Graph Neural Networks (GNNs) have been widely used in real-world applications, model explanations are required not only by users but also by legal regulations. However, simultaneously achieving high fidelity and low computational costs in generating explanations has been a challenge for current methods. In this work, we propose a framework of GNN explanation named LeArn Removal-based Attribution (LARA) to address this problem. Specifically, we introduce removal-based attribution and demonstrate its substantiated link to interpretability fidelity theoretically and experimentally. The explainer in LARA learns to generate removal-based attribution which enables providing explanations with high fidelity. A strategy of subgraph sampling is designed in LARA to improve the scalability of the training process. In the deployment, LARA can efficiently generate the explanation through a feed-forward pass. We benchmark our approach with other state-of-the-art GNN explanation methods on six datasets. Results highlight the effectiveness of our framework regarding both efficiency and fidelity. In particular, LARA is 3.1 \(\times\) faster and achieves higher fidelity than the state-of-the-art method on the large dataset ogbn-arxiv (more than 160K nodes and 1M edges), showing its great potential in real-world applications. Our source code is available at https://github.com/yaorong0921/LARA.
References
[1]
David Alvarez Melis and Tommi Jaakkola. Towards robust interpretability with self-explaining neural networks. Advances in neural information processing systems, 31, 2018.
[2]
Sebastian Bach, Alexander Binder, Grégoire Montavon, Frederick Klauschen, Klaus-Robert Müller, and Wojciech Samek. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS one, 10(7):e0130140, 2015.
[3]
Mohit Bajaj, Lingyang Chu, Zi Yu Xue, Jian Pei, Lanjun Wang, Peter Cho-Ho Lam, and Yong Zhang. Robust counterfactual explanations on graph neural networks. Advances in Neural Information Processing Systems, 34:5644–5655, 2021.
[4]
Albert-László Barabási and Réka Albert. Emergence of scaling in random networks. science, 286(5439):509–512, 1999.
[5]
Jianbo Chen, Le Song, Martin Wainwright, and Michael Jordan. Learning to explain: An information-theoretic perspective on model interpretation. In International Conference on Machine Learning, pages 883–892. PMLR, 2018.
[6]
Yu-Neng Chuang, Guanchu Wang, Fan Yang, Xuanting Cai, Tripathi Pushkar, and Xia Hu. CoRTX: Contrastive framework for real-time explanation. In Submitted to The Eleventh International Conference on Learning Representations, 2023. URL https://openreview.net/forum?id=L2MUOUp0beo. under review.
[7]
Yu-Neng Chuang, Guanchu Wang, Fan Yang, Zirui Liu, Xuanting Cai, Mengnan Du, and Xia Hu. Efficient xai techniques: A taxonomic survey. arXiv preprint arXiv:2302.03225, 2023.
[8]
Ian Covert, Scott M Lundberg, and Su-In Lee. Explaining by removing: A unified framework for model explanation. J. Mach. Learn. Res., 22:209–1, 2021.
[9]
Asim Kumar Debnath, Rosa L Lopez de Compadre, Gargi Debnath, Alan J Shusterman, and Corwin Hansch. 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.
[10]
Keyu Duan, Zirui Liu, Peihao Wang, Wenqing Zheng, Kaixiong Zhou, Tianlong Chen, Xia Hu, and Zhangyang Wang. A comprehensive study on large-scale graph training: Benchmarking and rethinking. arXiv preprint arXiv:2210.07494, 2022.
[11]
Alexandre Duval and Fragkiskos D Malliaros. Graphsvx: Shapley value explanations for graph neural networks. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 302–318. Springer, 2021.
[12]
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.
[13]
Qizhang Feng, Ninghao Liu, Fan Yang, Ruixiang Tang, Mengnan Du, and Xia Hu. Degree: Decomposition based explanation for graph neural networks. In International Conference on Learning Representations, 2021.
[14]
Thorben Funke, Megha Khosla, and Avishek Anand. Hard masking for explaining graph neural networks. 2020.
[15]
EU GDPR. Recital 71, 2016. URL https://www.privacy-regulation.eu/en/r71.htm.
[16]
Sara Hooker, Dumitru Erhan, Pieter-Jan Kindermans, and Been Kim. A benchmark for interpretability methods in deep neural networks. Advances in neural information processing systems, 32, 2019.
[17]
Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, and Jure Leskovec. Open graph benchmark: Datasets for machine learning on graphs. Advances in neural information processing systems, 33:22118–22133, 2020.
[18]
Qiang Huang, Makoto Yamada, Yuan Tian, Dinesh Singh, and Yi Chang. Graphlime: Local interpretable model explanations for graph neural networks. IEEE Transactions on Knowledge and Data Engineering, 2022.
[19]
Rundong Huang, Farhad Shirani, and Dongsheng Luo. Factorized explainer for graph neural networks. The 38th Annual AAAI Conference on Artificial Intelligence, 2024.
[20]
Neil Jethani, Mukund Sudarshan, Yindalon Aphinyanaphongs, and Rajesh Ranganath. Have we learned to explain?: How interpretability methods can learn to encode predictions in their interpretations. In International Conference on Artificial Intelligence and Statistics, pages 1459–1467. PMLR, 2021.
[21]
Neil Jethani, Mukund Sudarshan, Ian Connick Covert, Su-In Lee, and Rajesh Ranganath. Fastshap: Real-time shapley value estimation. In International Conference on Learning Representations, 2021.
[22]
Wanyu Lin, Hao Lan, and Baochun Li. Generative causal explanations for graph neural networks. In International Conference on Machine Learning, pages 6666–6679. PMLR, 2021.
[23]
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.
[24]
Ninghao Liu, Qizhang Feng, and Xia Hu. Interpretability in graph neural networks. Graph Neural Networks: Foundations, Frontiers, and Applications, pages 121–147, 2022.
[25]
Zirui Liu, Shengyuan Chen, Kaixiong Zhou, Daochen Zha, Xiao Huang, and Xia Hu. Rsc: Accelerating graph neural networks training via randomized sparse computations. arXiv preprint arXiv:2210.10737, 2022.
[26]
Zirui Liu, Kaixiong Zhou, Fan Yang, Li Li, Rui Chen, and Xia Hu. EXACT: Scalable graph neural networks training via extreme activation compression. In International Conference on Learning Representations, 2022. URL https://openreview.net/forum?id=vkaMaq95_rX.
[27]
Shengyao Lu, Keith G Mills, Jiao He, Bang Liu, and Di Niu. Goat: Explaining graph neural networks via graph output attribution. The International Conference on Learning Representations, 2024.
[28]
Scott M Lundberg and Su-In Lee. A unified approach to interpreting model predictions. Advances in neural information processing systems, 30, 2017.
[29]
Dongsheng Luo, Wei Cheng, Dongkuan Xu, Wenchao Yu, Bo Zong, Haifeng Chen, and Xiang Zhang. Parameterized explainer for graph neural network. Advances in neural information processing systems, 33:19620–19631, 2020.
[30]
Joao Marques-Silva and Alexey Ignatiev. Delivering trustworthy ai through formal xai. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 12342–12350, 2022.
[31]
Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems, 26, 2013.
[32]
Vitali Petsiuk, Abir Das, and Kate Saenko. Rise: Randomized input sampling for explanation of black-box models. arXiv preprint arXiv:1806.07421, 2018.
[33]
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/CVF Conference on Computer Vision and Pattern Recognition, pages 10772–10781, 2019.
[34]
Yao Rong, Tobias Leemann, Vadim Borisov, Gjergji Kasneci, and Enkelejda Kasneci. A consistent and efficient evaluation strategy for attribution methods. arXiv preprint arXiv:2202.00449, 2022.
[35]
Thomas Schnake, Oliver Eberle, Jonas Lederer, Shinichi Nakajima, Kristof T Schütt, Klaus-Robert Müller, and Grégoire Montavon. Higher-order explanations of graph neural networks via relevant walks. IEEE transactions on pattern analysis and machine intelligence, 44(11):7581–7596, 2021.
[36]
Richard Tomsett, Dan Harborne, Supriyo Chakraborty, Prudhvi Gurram, and Alun Preece. Sanity checks for saliency metrics. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 6021–6029, 2020.
[37]
Minh Vu and My T Thai. Pgm-explainer: Probabilistic graphical model explanations for graph neural networks. Advances in neural information processing systems, 33:12225–12235, 2020.
[38]
Guanchu Wang, Yu-Neng Chuang, Mengnan Du, Fan Yang, Quan Zhou, Pushkar Tripathi, Xuanting Cai, and Xia Hu. Accelerating shapley explanation via contributive cooperator selection. In International Conference on Machine Learning, pages 22576–22590. PMLR, 2022.
[39]
Xiang Wang, Yingxin Wu, An Zhang, Fuli Feng, Xiangnan He, and Tat-Seng Chua. Reinforced causal explainer for graph neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(2):2297–2309, 2022.
[40]
Fang Wu, Siyuan Li, Xurui Jin, Yinghui Jiang, Dragomir Radev, Zhangming Niu, and Stan Z Li. Rethinking explaining graph neural networks via non-parametric subgraph matching. In International Conference on Machine Learning, pages 37511–37523. PMLR, 2023.
[41]
Shiwen Wu, Fei Sun, Wentao Zhang, Xu Xie, and Bin Cui. Graph neural networks in recommender systems: a survey. ACM Computing Surveys, 55(5):1–37, 2022.
[42]
Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and S Yu Philip. A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems, 32(1):4–24, 2020.
[43]
Ping Xiong, Thomas Schnake, Michael Gastegger, Grégoire Montavon, Klaus Robert Muller, and Shinichi Nakajima. Relevant walk search for explaining graph neural networks. In International Conference on Machine Learning, pages 38301–38324. PMLR, 2023.
[44]
Makoto Yamada, Wittawat Jitkrittum, Leonid Sigal, Eric P Xing, and Masashi Sugiyama. High-dimensional feature selection by feature-wise kernelized lasso. Neural computation, 26(1):185–207, 2014.
[45]
Qiang Yang, Changsheng Ma, Qiannan Zhang, Xin Gao, Chuxu Zhang, and Xiangliang Zhang. Counterfactual learning on heterogeneous graphs with greedy perturbation. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 2988–2998, 2023.
[46]
Chih-Kuan Yeh, Cheng-Yu Hsieh, Arun Suggala, David I Inouye, and Pradeep K Ravikumar. On the (in) fidelity and sensitivity of explanations. Advances in Neural Information Processing Systems, 32, 2019.
[47]
Zhitao Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, and Jure Leskovec. Gnnexplainer: Generating explanations for graph neural networks. Advances in neural information processing systems, 32, 2019.
[48]
Jaemin Yoo, Meng-Chieh Lee, Shubhranshu Shekhar, and Christos Faloutsos. Less is more: Slimg for accurate, robust, and interpretable graph mining. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 3128–3139, 2023.
[49]
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.
[50]
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.
[51]
Hanqing Zeng, Hongkuan Zhou, Ajitesh Srivastava, Rajgopal Kannan, and Viktor Prasanna. Graphsaint: Graph sampling based inductive learning method. arXiv preprint arXiv:1907.04931, 2019.
[52]
Jiaxing Zhang, Dongsheng Luo, and Hua Wei. Mixupexplainer: Generalizing explanations for graph neural networks with data augmentation. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 3286–3296, 2023.
[53]
Shichang Zhang, Yozen Liu, Neil Shah, and Yizhou Sun. Gstarx: Explaining graph neural networks with structure-aware cooperative games. In Advances in Neural Information Processing Systems, 2022.
[54]
Yue Zhang, David Defazio, and Arti Ramesh. Relex: A model-agnostic relational model explainer. In Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society, pages 1042–1049, 2021.
[55]
Jianlong Zhou, Amir H Gandomi, Fang Chen, and Andreas Holzinger. Evaluating the quality of machine learning explanations: A survey on methods and metrics. Electronics, 10(5):593, 2021.
Index Terms
- Efficient GNN Explanation via Learning Removal-based Attribution
Recommendations
CI-GNN: A Granger causality-inspired graph neural network for interpretable brain network-based psychiatric diagnosis
AbstractThere is a recent trend to leverage the power of graph neural networks (GNNs) for brain-network based psychiatric diagnosis, which, in turn, also motivates an urgent need for psychiatrists to fully understand the decision behavior of the used ...
On Attribution of Recurrent Neural Network Predictions via Additive Decomposition
WWW '19: The World Wide Web ConferenceRNN models have achieved the state-of-the-art performance in a wide range of text mining tasks. However, these models are often regarded as black-boxes and are criticized due to the lack of interpretability. In this paper, we enhance the ...
Multi-objective Feature Attribution Explanation For Explainable Machine Learning
Special Issue on Explainable AI in Evolutionary ComputationThe feature attribution-based explanation (FAE) methods, which indicate how much each input feature contributes to the model’s output for a given data point, are one of the most popular categories of explainable machine learning techniques. Although ...
Comments
Information & Contributors
Information
Published In
EISSN:1556-472X
Table of ContentsCopyright © 2024 Copyright held by the owner/author(s).
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Online AM: 07 August 2024
Accepted: 25 July 2024
Revised: 24 May 2024
Received: 14 September 2023
Check for updates
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 62Total Downloads
- Downloads (Last 12 months)62
- Downloads (Last 6 weeks)62
Reflects downloads up to 13 Sep 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