{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T22:14:33Z","timestamp":1784585673348,"version":"3.55.0"},"reference-count":59,"publisher":"Association for Computing Machinery (ACM)","issue":"11","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2023,7]]},"abstract":"<jats:p>Deep graph networks (DGNs) have demonstrated their outstanding effectiveness on both heterogeneous and homogeneous graphs. However their black-box nature does not allow human users to understand their working mechanisms. Recently, extensive efforts have been devoted to explaining DGNs' prediction, yet heterogeneity-agnostic multi-level explainability is still less explored. Since the two types of graphs are both irreplaceable in real-life applications, having a more general and end-to-end explainer becomes a natural and inevitable choice. In the meantime, feature-level explanation is often ignored by existing techniques, while topological-level explanation alone can be incomplete and deceptive. Thus, we propose a heterogeneity-agnostic multi-level explainer in this paper, named HENCE-X, which is a causality-guided method that can capture the non-linear dependencies of model behavior on the input using conditional probabilities. We theoretically prove that HENCE-X is guaranteed to find the Markov blanket of the explained prediction, meaning that all information that the prediction is dependent on is identified. Experiments on three real-world datasets show that HENCE-X outperforms state-of-the-art (SOTA) methods in generating faithful factual and counterfactual explanations of DGNs.<\/jats:p>","DOI":"10.14778\/3611479.3611503","type":"journal-article","created":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T02:08:08Z","timestamp":1692929288000},"page":"2990-3003","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["HENCE-X: Toward Heterogeneity-Agnostic Multi-Level Explainability for Deep Graph Networks"],"prefix":"10.14778","volume":"16","author":[{"given":"Ge","family":"Lv","sequence":"first","affiliation":[{"name":"HKUST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen Jason","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dept. of Computing &amp; School of Hotel and Tourism Management, PolyU, Hong Kong Polytechnic University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Chen","sequence":"additional","affiliation":[{"name":"HKUST &amp; HKUST(GZ)"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,8,24]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"[n.d.]. Supplementary Materials. https:\/\/github.com\/Gori-LV\/HENCE-X.  [n.d.]. Supplementary Materials. https:\/\/github.com\/Gori-LV\/HENCE-X."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"e_1_2_1_3_1","first-page":"5644","article-title":"Robust counterfactual explanations on graph neural networks","volume":"34","author":"Bajaj Mohit","year":"2021","unstructured":"Mohit Bajaj , Lingyang Chu , Zi Yu Xue , Jian Pei , Lanjun Wang , Peter Cho-Ho Lam , and Yong Zhang . 2021 . Robust counterfactual explanations on graph neural networks . Advances in Neural Information Processing Systems 34 (2021), 5644 -- 5655 . Mohit Bajaj, Lingyang Chu, Zi Yu Xue, Jian Pei, Lanjun Wang, Peter Cho-Ho Lam, and Yong Zhang. 2021. Robust counterfactual explanations on graph neural networks. Advances in Neural Information Processing Systems 34 (2021), 5644--5655.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_4_1","volume-title":"Sensitivity analysis in linear regression","author":"Chatterjee Samprit","unstructured":"Samprit Chatterjee . 1988. Sensitivity analysis in linear regression . Wiley , New York . Samprit Chatterjee. 1988. Sensitivity analysis in linear regression. Wiley, New York."},{"key":"e_1_2_1_5_1","volume-title":"From complex questionnaire and interviewing data to intelligent Bayesian network models for medical decision support. Artificial intelligence in medicine 67","author":"Constantinou Anthony Costa","year":"2016","unstructured":"Anthony Costa Constantinou , Norman Fenton , William Marsh , and Lukasz Radlinski . 2016. From complex questionnaire and interviewing data to intelligent Bayesian network models for medical decision support. Artificial intelligence in medicine 67 ( 2016 ), 75--93. Anthony Costa Constantinou, Norman Fenton, William Marsh, and Lukasz Radlinski. 2016. From complex questionnaire and interviewing data to intelligent Bayesian network models for medical decision support. Artificial intelligence in medicine 67 (2016), 75--93."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1021\/jm00106a046"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.371"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380297"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/0951-8320(96)00002-6"},{"key":"e_1_2_1_10_1","volume-title":"HSDN: A High-Order Structural Semantic Disentangled Neural Network","author":"Hu Bingde","year":"2022","unstructured":"Bingde Hu , Xingen Wang , Zunlei Feng , Jie Song , Ji Zhao , Mingli Song , and Xinyu Wang . 2022 . HSDN: A High-Order Structural Semantic Disentangled Neural Network . IEEE Transactions on Knowledge and Data Engineering ( 2022). Bingde Hu, Xingen Wang, Zunlei Feng, Jie Song, Ji Zhao, Mingli Song, and Xinyu Wang. 2022. HSDN: A High-Order Structural Semantic Disentangled Neural Network. IEEE Transactions on Knowledge and Data Engineering (2022)."},{"key":"e_1_2_1_11_1","volume-title":"GCN-LRP explanation: exploring latent attention of graph convolutional networks","author":"Hu Jinlong","unstructured":"Jinlong Hu , Tenghui Li , and Shoubin Dong . 2020. GCN-LRP explanation: exploring latent attention of graph convolutional networks . In IJCNN. IEEE , 1--8. Jinlong Hu, Tenghui Li, and Shoubin Dong. 2020. GCN-LRP explanation: exploring latent attention of graph convolutional networks. In IJCNN. IEEE, 1--8."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380027"},{"key":"e_1_2_1_13_1","first-page":"956","article-title":"Structure Learning of Bayesian Network","volume":"7","author":"Kareem Shahab Wahhab","year":"2022","unstructured":"Shahab Wahhab Kareem , Farah Qasim Ahmed Alyousuf , Kosrat Ahmad , Roojwan Hawezi , and Hoshang Qasim Awla . 2022 . Structure Learning of Bayesian Network : A Review. QALAAI ZANIST JOURNAL 7 , 1 (2022), 956 -- 975 . Shahab Wahhab Kareem, Farah Qasim Ahmed Alyousuf, Kosrat Ahmad, Roojwan Hawezi, and Hoshang Qasim Awla. 2022. Structure Learning of Bayesian Network: A Review. QALAAI ZANIST JOURNAL 7, 1 (2022), 956--975.","journal-title":"A Review. QALAAI ZANIST JOURNAL"},{"key":"e_1_2_1_14_1","volume-title":"Semi-Supervised Classification with Graph Convolutional Networks. In 5th International Conference on Learning Representations, ICLR","author":"Thomas","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017 . Semi-Supervised Classification with Graph Convolutional Networks. In 5th International Conference on Learning Representations, ICLR 2017 . OpenReview.net. Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In 5th International Conference on Learning Representations, ICLR 2017. OpenReview.net."},{"key":"e_1_2_1_15_1","volume-title":"Probabilistic graphical models: principles and techniques","author":"Koller Daphne","unstructured":"Daphne Koller and Nir Friedman . 2009. Probabilistic graphical models: principles and techniques . MIT press . Daphne Koller and Nir Friedman. 2009. Probabilistic graphical models: principles and techniques. MIT press."},{"key":"e_1_2_1_16_1","volume-title":"Explainable Artificial Intelligence: An Updated Perspective","author":"Krajna Agneza","unstructured":"Agneza Krajna , Mihael Kovac , Mario Brcic , and Ana Sarcevic . 2022. Explainable Artificial Intelligence: An Updated Perspective . In MIPRO. IEEE , 859--864. Agneza Krajna, Mihael Kovac, Mario Brcic, and Ana Sarcevic. 2022. Explainable Artificial Intelligence: An Updated Perspective. In MIPRO. IEEE, 859--864."},{"key":"e_1_2_1_17_1","volume-title":"Contributions to the Theory of Games","author":"Kuhn Harold William","unstructured":"Harold William Kuhn and Albert William Tucker . 1953. Contributions to the Theory of Games . Vol. 2 . Princeton University Press . Harold William Kuhn and Albert William Tucker. 1953. Contributions to the Theory of Games. Vol. 2. Princeton University Press."},{"key":"e_1_2_1_18_1","volume-title":"Disentangled graph neural networks for session-based recommendation","author":"Li Ansong","year":"2022","unstructured":"Ansong Li , Zhiyong Cheng , Fan Liu , Zan Gao , Weili Guan , and Yuxin Peng . 2022. Disentangled graph neural networks for session-based recommendation . IEEE Transactions on Knowledge and Data Engineering ( 2022 ). Ansong Li, Zhiyong Cheng, Fan Liu, Zan Gao, Weili Guan, and Yuxin Peng. 2022. Disentangled graph neural networks for session-based recommendation. IEEE Transactions on Knowledge and Data Engineering (2022)."},{"key":"e_1_2_1_19_1","volume-title":"Learning ancestral polytrees. Learning Tractable Probabilistic Models","author":"Li Guangdi","year":"2014","unstructured":"Guangdi Li , Anne-Mieke Vandamme , and Jan Ramon . 2014. Learning ancestral polytrees. Learning Tractable Probabilistic Models ( 2014 ). Guangdi Li, Anne-Mieke Vandamme, and Jan Ramon. 2014. Learning ancestral polytrees. Learning Tractable Probabilistic Models (2014)."},{"key":"e_1_2_1_20_1","volume-title":"Understanding neural networks through representation erasure. arXiv preprint arXiv:1612.08220","author":"Li Jiwei","year":"2016","unstructured":"Jiwei Li , Will Monroe , and Dan Jurafsky . 2016. Understanding neural networks through representation erasure. arXiv preprint arXiv:1612.08220 ( 2016 ). Jiwei Li, Will Monroe, and Dan Jurafsky. 2016. Understanding neural networks through representation erasure. arXiv preprint arXiv:1612.08220 (2016)."},{"key":"e_1_2_1_21_1","volume-title":"International Conference on Machine Learning. PMLR, 6666--6679","author":"Lin Wanyu","year":"2021","unstructured":"Wanyu Lin , Hao Lan , and Baochun Li . 2021 . Generative causal explanations for graph neural networks . In International Conference on Machine Learning. PMLR, 6666--6679 . Wanyu Lin, Hao Lan, and Baochun Li. 2021. Generative causal explanations for graph neural networks. In International Conference on Machine Learning. PMLR, 6666--6679."},{"key":"e_1_2_1_22_1","volume-title":"Gabriele Tolomei, Maarten de Rijke, and Fabrizio Silvestri.","author":"Lucic Ana","year":"2021","unstructured":"Ana Lucic , Maartje ter Hoeve , Gabriele Tolomei, Maarten de Rijke, and Fabrizio Silvestri. 2021 . CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks . arXiv preprint arXiv:2102.03322 (2021). Ana Lucic, Maartje ter Hoeve, Gabriele Tolomei, Maarten de Rijke, and Fabrizio Silvestri. 2021. CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks. arXiv preprint arXiv:2102.03322 (2021)."},{"key":"e_1_2_1_23_1","volume-title":"Parameterized Explainer for Graph Neural Network. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems","author":"Luo Dongsheng","year":"2020","unstructured":"Dongsheng Luo , Wei Cheng , Dongkuan Xu , Wenchao Yu , Bo Zong , Haifeng Chen , and Xiang Zhang . 2020 . Parameterized Explainer for Graph Neural Network. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020. Dongsheng Luo, Wei Cheng, Dongkuan Xu, Wenchao Yu, Bo Zong, Haifeng Chen, and Xiang Zhang. 2020. Parameterized Explainer for Graph Neural Network. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020."},{"key":"e_1_2_1_24_1","unstructured":"Qingsong Lv Ming Ding Qiang Liu Yuxiang Chen Wenzheng Feng Siming He Chang Zhou Jianguo Jiang Yuxiao Dong and Jie Tang. 2021. Are we really making much progress?: Revisiting benchmarking and refining heterogeneous graph neural networks. In KDD. ACM 1150--1160.  Qingsong Lv Ming Ding Qiang Liu Yuxiang Chen Wenzheng Feng Siming He Chang Zhou Jianguo Jiang Yuxiao Dong and Jie Tang. 2021. Are we really making much progress?: Revisiting benchmarking and refining heterogeneous graph neural networks. In KDD. ACM 1150--1160."},{"key":"e_1_2_1_25_1","volume-title":"Bayesian network induction via local neighborhoods. Advances in neural information processing systems 12","author":"Margaritis Dimitris","year":"1999","unstructured":"Dimitris Margaritis and Sebastian Thrun . 1999. Bayesian network induction via local neighborhoods. Advances in neural information processing systems 12 ( 1999 ). Dimitris Margaritis and Sebastian Thrun. 1999. Bayesian network induction via local neighborhoods. Advances in neural information processing systems 12 (1999)."},{"key":"e_1_2_1_26_1","volume-title":"G-test of goodness-of-fit. Handbook of biological statistics 487","author":"McDonald John H","year":"2014","unstructured":"John H McDonald . 2014. G-test of goodness-of-fit. Handbook of biological statistics 487 ( 2014 ), 53--58. John H McDonald. 2014. G-test of goodness-of-fit. Handbook of biological statistics 487 (2014), 53--58."},{"key":"e_1_2_1_27_1","volume-title":"Small numbers in chi-square and G-tests. Handbook of biological statistics","author":"McDonald John H","year":"2014","unstructured":"John H McDonald . 2014. Small numbers in chi-square and G-tests. Handbook of biological statistics ( 2014 ), 86--89. John H McDonald. 2014. Small numbers in chi-square and G-tests. Handbook of biological statistics (2014), 86--89."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2014.2321179"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888900003039"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-39963-1_66"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2004.01.001"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-08-051489-5.50009-6"},{"key":"e_1_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Judea Pearl. 1988. Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan kaufmann.  Judea Pearl. 1988. Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan kaufmann.","DOI":"10.1016\/B978-0-08-051489-5.50008-4"},{"key":"e_1_2_1_34_1","volume-title":"Cambridge, UK: CambridgeUniversityPress 19, 2","author":"Judea Pearl","year":"2000","unstructured":"Judea Pearl et al. 2000 . Models , reasoning and inference. Cambridge, UK: CambridgeUniversityPress 19, 2 (2000). Judea Pearl et al. 2000. Models, reasoning and inference. Cambridge, UK: CambridgeUniversityPress 19, 2 (2000)."},{"key":"e_1_2_1_35_1","volume-title":"Explainability Methods for Graph Convolutional Neural Networks. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR","author":"Pope Phillip E.","year":"2019","unstructured":"Phillip E. Pope , Soheil Kolouri , Mohammad Rostami , Charles E. Martin , and Heiko Hoffmann . 2019 . Explainability Methods for Graph Convolutional Neural Networks. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019. Computer Vision Foundation \/ IEEE, 10772--10781. Phillip E. Pope, Soheil Kolouri, Mohammad Rostami, Charles E. Martin, and Heiko Hoffmann. 2019. Explainability Methods for Graph Convolutional Neural Networks. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019. Computer Vision Foundation \/ IEEE, 10772--10781."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.14778\/3494124.3494128"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/0888-613X(88)90158-2"},{"key":"e_1_2_1_38_1","unstructured":"John T. Roscoe. 1975. Fundamental research statistics for the behavioral sciences. Holt Rinehart and Winston.  John T. Roscoe. 1975. Fundamental research statistics for the behavioral sciences. Holt Rinehart and Winston."},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.2307\/1270993"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13748-019-00194-y"},{"key":"e_1_2_1_41_1","unstructured":"Uma Sekaran and Roger Bougie. 2016. Research methods for business: A skill building approach. john wiley & sons.  Uma Sekaran and Roger Bougie. 2016. Research methods for business: A skill building approach. john wiley & sons."},{"key":"e_1_2_1_42_1","volume-title":"Reinforcement Learning Enhanced Explainer for Graph Neural Networks. Advances in Neural Information Processing Systems 34","author":"Shan Caihua","year":"2021","unstructured":"Caihua Shan , Yifei Shen , Yao Zhang , Xiang Li , and Dongsheng Li. 2021. Reinforcement Learning Enhanced Explainer for Graph Neural Networks. Advances in Neural Information Processing Systems 34 ( 2021 ). Caihua Shan, Yifei Shen, Yao Zhang, Xiang Li, and Dongsheng Li. 2021. Reinforcement Learning Enhanced Explainer for Graph Neural Networks. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-018-0711-6"},{"key":"e_1_2_1_44_1","unstructured":"Masami Takikawa and Bruce D'Ambrosio. 1999. Multiplicative Factorization of Noisy-Max. In UAI. Morgan Kaufmann 622--630.  Masami Takikawa and Bruce D'Ambrosio. 1999. Multiplicative Factorization of Noisy-Max. In UAI. Morgan Kaufmann 622--630."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511948"},{"key":"e_1_2_1_46_1","volume-title":"Graph Attention Networks. In 6th International Conference on Learning Representations, ICLR","author":"Velickovic Petar","year":"2018","unstructured":"Petar Velickovic , Guillem Cucurull , Arantxa Casanova , Adriana Romero , Pietro Li\u00f2 , and Yoshua Bengio . 2018 . Graph Attention Networks. In 6th International Conference on Learning Representations, ICLR 2018. OpenReview.net. Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph Attention Networks. In 6th International Conference on Learning Representations, ICLR 2018. OpenReview.net."},{"key":"e_1_2_1_47_1","volume-title":"PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems","author":"Minh","year":"2020","unstructured":"Minh N. Vu and My T. Thai. 2020 . PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020 . Minh N. Vu and My T. Thai. 2020. PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020."},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-75256-1_45"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313562"},{"key":"e_1_2_1_50_1","unstructured":"Xiang Wang Ying-Xin Wu An Zhang Xiangnan He and Tat-Seng Chua. 2021. Towards Multi-Grained Explainability for Graph Neural Networks. In NeurIPS. 18446--18458.  Xiang Wang Ying-Xin Wu An Zhang Xiangnan He and Tat-Seng Chua. 2021. Towards Multi-Grained Explainability for Graph Neural Networks. In NeurIPS. 18446--18458."},{"key":"e_1_2_1_51_1","volume-title":"Towards Multi-Grained Explainability for Graph Neural Networks. Advances in Neural Information Processing Systems 34","author":"Wang Xiang","year":"2021","unstructured":"Xiang Wang , Yingxin Wu , An Zhang , Xiangnan He , and Tat-Seng Chua . 2021. Towards Multi-Grained Explainability for Graph Neural Networks. Advances in Neural Information Processing Systems 34 ( 2021 ). Xiang Wang, Yingxin Wu, An Zhang, Xiangnan He, and Tat-Seng Chua. 2021. Towards Multi-Grained Explainability for Graph Neural Networks. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_2_1_52_1","unstructured":"Xiang Wang An Zhang Xia Hu Fuli Feng Xiangnan He Tat-Seng Chua etal 2022. Deconfounding to Explanation Evaluation in Graph Neural Networks. arXiv preprint arXiv:2201.08802 (2022).  Xiang Wang An Zhang Xia Hu Fuli Feng Xiangnan He Tat-Seng Chua et al. 2022. Deconfounding to Explanation Evaluation in Graph Neural Networks. arXiv preprint arXiv:2201.08802 (2022)."},{"key":"e_1_2_1_53_1","unstructured":"Keyulu Xu Weihua Hu Jure Leskovec and Stefanie Jegelka. 2019. How Powerful are Graph Neural Networks?. In ICLR.  Keyulu Xu Weihua Hu Jure Leskovec and Stefanie Jegelka. 2019. How Powerful are Graph Neural Networks?. In ICLR."},{"key":"e_1_2_1_54_1","volume-title":"GNNExplainer: Generating Explanations for Graph Neural Networks. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Ying Zhitao","year":"2019","unstructured":"Zhitao Ying , Dylan Bourgeois , Jiaxuan You , Marinka Zitnik , and Jure Leskovec . 2019 . GNNExplainer: Generating Explanations for Graph Neural Networks. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019 , NeurIPS 2019. Zhitao Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, and Jure Leskovec. 2019. GNNExplainer: Generating Explanations for Graph Neural Networks. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019."},{"key":"e_1_2_1_55_1","volume-title":"XGNN: Towards Model-Level Explanations of Graph Neural Networks. In KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Yuan Hao","year":"2020","unstructured":"Hao Yuan , Jiliang Tang , Xia Hu , and Shuiwang Ji . 2020 . XGNN: Towards Model-Level Explanations of Graph Neural Networks. In KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining , Virtual Event , 2020. ACM, 430--438. Hao Yuan, Jiliang Tang, Xia Hu, and Shuiwang Ji. 2020. XGNN: Towards Model-Level Explanations of Graph Neural Networks. In KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event, 2020. ACM, 430--438."},{"key":"e_1_2_1_56_1","volume-title":"Explainability in graph neural networks: A taxonomic survey","author":"Yuan Hao","year":"2022","unstructured":"Hao Yuan , Haiyang Yu , Shurui Gui , and Shuiwang Ji. 2022. Explainability in graph neural networks: A taxonomic survey . IEEE Transactions on Pattern Analysis and Machine Intelligence ( 2022 ). Hao Yuan, Haiyang Yu, Shurui Gui, and Shuiwang Ji. 2022. Explainability in graph neural networks: A taxonomic survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)."},{"key":"e_1_2_1_57_1","unstructured":"Hao Yuan Haiyang Yu Jie Wang Kang Li and Shuiwang Ji. 2020. On Explainability of Graph Neural Networks via Subgraph Explorations. In ICML (Proceedings of Machine Learning Research).  Hao Yuan Haiyang Yu Jie Wang Kang Li and Shuiwang Ji. 2020. On Explainability of Graph Neural Networks via Subgraph Explorations. In ICML (Proceedings of Machine Learning Research)."},{"key":"e_1_2_1_58_1","first-page":"11983","article-title":"Graph transformer networks","volume":"32","author":"Yun Seongjun","year":"2019","unstructured":"Seongjun Yun , Minbyul Jeong , Raehyun Kim , Jaewoo Kang , and Hyunwoo J Kim . 2019 . Graph transformer networks . Advances in Neural Information Processing Systems 32 (2019), 11983 -- 11993 . Seongjun Yun, Minbyul Jeong, Raehyun Kim, Jaewoo Kang, and Hyunwoo J Kim. 2019. Graph transformer networks. Advances in Neural Information Processing Systems 32 (2019), 11983--11993.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622756.1622765"}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3611479.3611503","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,23]],"date-time":"2023-09-23T22:22:58Z","timestamp":1695507778000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3611479.3611503"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":59,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["10.14778\/3611479.3611503"],"URL":"https:\/\/doi.org\/10.14778\/3611479.3611503","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2023,7]]},"assertion":[{"value":"2023-08-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}