{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T22:14:39Z","timestamp":1784585679365,"version":"3.55.0"},"reference-count":71,"publisher":"Association for Computing Machinery (ACM)","issue":"5","funder":[{"name":"National Science Foundation","award":["IIS 1817046"],"award-info":[{"award-number":["IIS 1817046"]}]},{"name":"National Science Foundation","award":["IIS 2229876"],"award-info":[{"award-number":["IIS 2229876"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2025,10,31]]},"abstract":"<jats:p>\n            Graph neural networks (GNNs) find applications in various domains such as computational biology, natural language processing, and computer security. Owing to their popularity, there is an increasing need to explain GNN predictions since GNNs are black-box machine learning models. One way to address this issue involves using\n            <jats:italic toggle=\"yes\">counterfactual<\/jats:italic>\n            reasoning where the objective is to alter the GNN prediction by minimal changes in the input graph. Existing methods for counterfactual explanation of GNNs are limited to instance-specific\n            <jats:italic toggle=\"yes\">local<\/jats:italic>\n            reasoning. This approach has two major limitations of not being able to offer global recourse policies and overloading human cognitive ability with too much information. In this work, we study the\n            <jats:italic toggle=\"yes\">global<\/jats:italic>\n            explainability of GNNs through global counterfactual reasoning. Specifically, we want to find a\n            <jats:italic toggle=\"yes\">small<\/jats:italic>\n            set of representative counterfactual graphs that explains\n            <jats:italic toggle=\"yes\">all<\/jats:italic>\n            input graphs. Toward this goal, we propose\n            <jats:sc>GCFExplainer<\/jats:sc>\n            , a novel algorithm powered by\n            <jats:italic toggle=\"yes\">vertex-reinforced random walks<\/jats:italic>\n            on an\n            <jats:italic toggle=\"yes\">edit map<\/jats:italic>\n            of graphs with a\n            <jats:italic toggle=\"yes\">greedy summary<\/jats:italic>\n            . Extensive experiments on real graph datasets show that the global explanation from\n            <jats:sc>GCFExplainer<\/jats:sc>\n            provides important high-level insights of the model behavior and achieves a\n            <jats:italic toggle=\"yes\">46.9%<\/jats:italic>\n            gain in recourse coverage, a\n            <jats:italic toggle=\"yes\">9.5%<\/jats:italic>\n            reduction in recourse cost compared to the state-of-the-art local counterfactual explainers. We also demonstrate that\n            <jats:sc>GCFExplainer<\/jats:sc>\n            generates explanations that are more consistent with input dataset characteristics, and is robust under adversarial attacks. In addition,\n            <jats:sc>K-GCFExplainer<\/jats:sc>\n            , which incorporates a graph clustering component into\n            <jats:sc>GCFExplainer<\/jats:sc>\n            , is introduced as a more competitive extension for datasets with a clustering structure, leading to superior performance in three out of four datasets in the experiments and better scalability.\n          <\/jats:p>","DOI":"10.1145\/3698108","type":"journal-article","created":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T05:39:41Z","timestamp":1727761181000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["GCFExplainer: Global Counterfactual Explainer for Graph Neural Networks"],"prefix":"10.1145","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8092-5024","authenticated-orcid":false,"given":"Mert","family":"Kosan","sequence":"first","affiliation":[{"name":"University of California, Santa Barbara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1480-4494","authenticated-orcid":false,"given":"Zexi","family":"Huang","sequence":"additional","affiliation":[{"name":"University of California, Santa Barbara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0996-2807","authenticated-orcid":false,"given":"Sourav","family":"Medya","sequence":"additional","affiliation":[{"name":"University of Illinois, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4147-9372","authenticated-orcid":false,"given":"Sayan","family":"Ranu","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology, Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1997-7140","authenticated-orcid":false,"given":"Ambuj","family":"Singh","sequence":"additional","affiliation":[{"name":"University of California, Santa Barbara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,18]]},"reference":[{"key":"e_1_3_1_2_1","article-title":"Counterfactual graphs for explainable classification of brain networks","author":"Abrate Carlo","year":"2021","unstructured":"Carlo Abrate and Francesco Bonchi. 2021. Counterfactual graphs for explainable classification of brain networks. In SIGKDD.","journal-title":"SIGKDD"},{"key":"e_1_3_1_3_1","article-title":"Robust counterfactual explanations on graph neural networks","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. In NeurIPS.","journal-title":"NeurIPS"},{"key":"e_1_3_1_4_1","article-title":"Learning articulated rigid body dynamics with lagrangian graph neural network","author":"Bhattoo Ravinder","year":"2022","unstructured":"Ravinder Bhattoo, Sayan Ranu, and N. M. Krishnan. 2022. Learning articulated rigid body dynamics with lagrangian graph neural network. In NeurIPS.","journal-title":"NeurIPS"},{"key":"e_1_3_1_5_1","first-page":"11069","volume-title":"AAAI","volume":"38","author":"Bhowmick Aritra","year":"2024","unstructured":"Aritra Bhowmick, Mert Kosan, Zexi Huang, Ambuj Singh, and Sourav Medya. 2024. DGCLUSTER: A neural framework for attributed graph clustering via modularity maximization. In AAAI, Vol. 38, 11069\u201311077."},{"key":"e_1_3_1_6_1","article-title":"Adversarial attacks on node embeddings via graph poisoning","author":"Bojchevski Aleksandar","year":"2019","unstructured":"Aleksandar Bojchevski and Stephan G\u00fcnnemann. 2019. Adversarial attacks on node embeddings via graph poisoning. In ICML.","journal-title":"ICML"},{"key":"e_1_3_1_7_1","article-title":"Fast computation of graph kernels","author":"Borgwardt Karsten","year":"2006","unstructured":"Karsten Borgwardt, Nicol Schraudolph, and S. V. N. Vishwanathan. 2006. Fast computation of graph kernels. In NeurIPS.","journal-title":"NeurIPS"},{"issue":"1","key":"e_1_3_1_8_1","first-page":"i47\u2013i56","article-title":"Protein function prediction via graph kernels","volume":"21","author":"Borgwardt Karsten M.","year":"2005","unstructured":"Karsten M. Borgwardt, Cheng Soon Ong, Stefan Sch\u00f6nauer, S. V. N. Vishwanathan, Alex J. Smola, and Hans-Peter Kriegel. 2005. Protein function prediction via graph kernels. Bioinformatics 21, suppl 1 (2005), i47\u2013i56.","journal-title":"Bioinformatics"},{"key":"e_1_3_1_9_1","article-title":"Fast neighborhood subgraph pairwise distance kernel","author":"Costa Fabrizio","year":"2010","unstructured":"Fabrizio Costa and Kurt De Grave. 2010. Fast neighborhood subgraph pairwise distance kernel. In ICML.","journal-title":"ICML"},{"key":"e_1_3_1_10_1","article-title":"Adversarial attack on graph structured data","author":"Dai Hanjun","year":"2018","unstructured":"Hanjun Dai, Hui Li, Tian Tian, Xin Huang, Lin Wang, Jun Zhu, and Le Song. 2018. Adversarial attack on graph structured data. In ICML.","journal-title":"ICML"},{"key":"e_1_3_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-2836(03)00628-4"},{"key":"e_1_3_1_12_1","first-page":"1","article-title":"Counterfactual explanations and how to find them: Literature review and benchmarking","author":"Guidotti Riccardo","year":"2022","unstructured":"Riccardo Guidotti. 2022. Counterfactual explanations and how to find them: Literature review and benchmarking. Data Mining and Knowledge Discovery (2022), 1\u201355.","journal-title":"Data Mining and Knowledge Discovery"},{"key":"e_1_3_1_13_1","article-title":"TIGGER: Scalable generative modelling for temporal interaction graphs","author":"Gupta Shubham","year":"2022","unstructured":"Shubham Gupta, Sahil Manchanda, Srikanta Bedathur, and Sayan Ranu. 2022. TIGGER: Scalable generative modelling for temporal interaction graphs. In AAAI.","journal-title":"AAAI"},{"key":"e_1_3_1_14_1","article-title":"Inductive representation learning on large graphs","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In NeurIPS.","journal-title":"NeurIPS"},{"key":"e_1_3_1_15_1","article-title":"Global counterfactual explainer for graph neural networks","author":"Huang Zexi","year":"2023","unstructured":"Zexi Huang, Mert Kosan, Sourav Medya, Sayan Ranu, and Ambuj Singh. 2023. Global counterfactual explainer for graph neural networks. In WSDM.","journal-title":"WSDM"},{"key":"e_1_3_1_16_1","article-title":"A broader picture of random-walk based graph embedding","author":"Huang Zexi","year":"2021","unstructured":"Zexi Huang, Arlei Silva, and Ambuj Singh. 2021. A broader picture of random-walk based graph embedding. In SIGKDD.","journal-title":"SIGKDD"},{"key":"e_1_3_1_17_1","article-title":"POLE: Polarized embedding for signed networks","author":"Huang Zexi","year":"2022","unstructured":"Zexi Huang, Arlei Silva, and Ambuj Singh. 2022. POLE: Polarized embedding for signed networks. In WSDM.","journal-title":"WSDM"},{"key":"e_1_3_1_18_1","first-page":"35","article-title":"Drug\u2013target affinity prediction using graph neural network and contact maps","volume":"10","author":"Jiang Mingjian","year":"2020","unstructured":"Mingjian Jiang, Zhen Li, Shugang Zhang, Shuang Wang, Xiaofeng Wang, Qing Yuan, and Zhiqiang Wei. 2020. Drug\u2013target affinity prediction using graph neural network and contact maps. RSC Advances 10, 35 (2020), 20701\u201320712.","journal-title":"RSC Advances"},{"key":"e_1_3_1_19_1","unstructured":"Jaykumar Kakkad Jaspal Jannu Kartik Sharma Charu Aggarwal and Sourav Medya. 2023. A survey on explainability of graph neural networks. arXiv:2306.01958. Retrieved from https:\/\/arxiv.org\/pdf\/2306.01958"},{"key":"e_1_3_1_20_1","article-title":"Model-agnostic counterfactual explanations for consequential decisions","author":"Karimi Amir-Hossein","year":"2020","unstructured":"Amir-Hossein Karimi, Gilles Barthe, Borja Balle, and Isabel Valera. 2020. Model-agnostic counterfactual explanations for consequential decisions. In AISTATS.","journal-title":"AISTATS"},{"key":"e_1_3_1_21_1","doi-asserted-by":"publisher","DOI":"10.1021\/jm040835a"},{"key":"e_1_3_1_22_1","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980. Retrieved from https:\/\/arxiv.org\/pdf\/1412.6980"},{"key":"e_1_3_1_23_1","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In ICLR.","journal-title":"ICLR"},{"key":"e_1_3_1_24_1","article-title":"Predict then propagate: Graph neural networks meet personalized pagerank","author":"Klicpera Johannes","year":"2018","unstructured":"Johannes Klicpera, Aleksandar Bojchevski, and Stephan G\u00fcnnemann. 2018. Predict then propagate: Graph neural networks meet personalized pagerank. In ICLR.","journal-title":"ICLR"},{"key":"e_1_3_1_25_1","unstructured":"Mert Kosan Arlei Silva Sourav Medya Brian Uzzi and Ambuj Singh. 2021. Event detection on dynamic graphs. arXiv:2110.12148. Retrieved from https:\/\/arxiv.org\/pdf\/2110.12148"},{"key":"e_1_3_1_26_1","volume-title":"ICLR","author":"Kosan Mert","year":"2024","unstructured":"Mert Kosan, Samidha Verma, Burouj Armgaan, Khushbu Pahwa, Ambuj Singh, Sourav Medya, and Sayan Ranu. 2024. GNNX-BENCH: Unravelling the utility of perturbation-based GNN explainers through in-depth benchmarking. In ICLR."},{"key":"e_1_3_1_27_1","first-page":"19315","volume-title":"ICML","author":"Ley Dan","year":"2023","unstructured":"Dan Ley, Saumitra Mishra, and Daniele Magazzeni. 2023. GLOBE-CE: A translation based approach for global counterfactual explanations. In ICML. PMLR, 19315\u201319342."},{"key":"e_1_3_1_28_1","first-page":"783","article-title":"Similarity search in graph databases: A multi-layered indexing approach","author":"Liang Yongjiang","year":"2017","unstructured":"Yongjiang Liang and Peixiang Zhao. 2017. Similarity search in graph databases: A multi-layered indexing approach. In ICDE, 783\u2013794.","journal-title":"ICDE"},{"key":"e_1_3_1_29_1","unstructured":"Wanyu Lin Hao Lan and Baochun Li. 2021. Generative causal explanations for graph neural networks. In ICML. PMLR 6666\u20136679."},{"key":"e_1_3_1_30_1","article-title":"CF-GNNExplainer: Counterfactual explanations for graph neural networks","author":"Lucic Ana","year":"2022","unstructured":"Ana Lucic, Maartje A. Ter Hoeve, Gabriele Tolomei, Maarten De Rijke, and Fabrizio Silvestri. 2022. CF-GNNExplainer: Counterfactual explanations for graph neural networks. In AISTATS.","journal-title":"AISTATS"},{"key":"e_1_3_1_31_1","article-title":"Parameterized explainer for graph neural network","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 NeurIPS.","journal-title":"NeurIPS"},{"key":"e_1_3_1_32_1","unstructured":"Jing Ma Ruocheng Guo Saumitra Mishra Aidong Zhang and Jundong Li. 2022. CLEAR: Generative counterfactual explanations on graphs. arXiv:2210.08443. Retrieved from https:\/\/arxiv.org\/pdf\/2210.08443"},{"key":"e_1_3_1_33_1","article-title":"GCOMB: Learning budget-constrained combinatorial algorithms over billion-sized graphs","author":"Manchanda Sahil","year":"2020","unstructured":"Sahil Manchanda, Akash Mittal, Anuj Dhawan, Sourav Medya, Sayan Ranu, and Ambuj Singh. 2020. GCOMB: Learning budget-constrained combinatorial algorithms over billion-sized graphs. In NeurIPS.","journal-title":"NeurIPS"},{"key":"e_1_3_1_34_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.93.012306"},{"key":"e_1_3_1_35_1","article-title":"An exploratory study of stock price movements from earnings calls","author":"Medya Sourav","year":"2022","unstructured":"Sourav Medya, Mohammad Rasoolinejad, Yang Yang, and Brian Uzzi. 2022. An exploratory study of stock price movements from earnings calls. In WebConf.","journal-title":"WebConf"},{"key":"e_1_3_1_36_1","article-title":"Divrank: The interplay of prestige and diversity in information networks","author":"Mei Qiaozhu","year":"2010","unstructured":"Qiaozhu Mei, Jian Guo, and Dragomir Radev. 2010. Divrank: The interplay of prestige and diversity in information networks. In SIGKDD.","journal-title":"SIGKDD"},{"key":"e_1_3_1_37_1","article-title":"Efficient computation of frequent and top-k elements in data streams","author":"Metwally Ahmed","year":"2005","unstructured":"Ahmed Metwally, Divyakant Agrawal, and Amr El Abbadi. 2005. Efficient computation of frequent and top-k elements in data streams. In ICDT.","journal-title":"ICDT"},{"key":"e_1_3_1_38_1","unstructured":"Azalia Mirhoseini Anna Goldie Mustafa Yazgan Joe W. J. Jiang Ebrahim M. Songhori Shen Wang Young-Joon Lee Eric Johnson Omkar Pathak Sungmin Bae Azade Nazi Jiwoo Pak Andy Tong Kavya Srinivasa William Hang Emre Tuncer Anand Babu Quoc V. Le James Laudon Richard Ho Roger Carpenter and Jeff Dean. 2020. Chip placement with deep reinforcement learning. arXiv:2004.10746."},{"key":"e_1_3_1_39_1","article-title":"A scalable and generic framework to mine top-k representative subgraph patterns","author":"Natarajan Dheepikaa","year":"2016","unstructured":"Dheepikaa Natarajan and Sayan Ranu. 2016. A scalable and generic framework to mine top-k representative subgraph patterns. In ICDM.","journal-title":"ICDM"},{"key":"e_1_3_1_40_1","article-title":"GraphReach: Position-aware graph neural network using reachability estimations","author":"Nishad Sunil","year":"2021","unstructured":"Sunil Nishad, Shubhangi Agarwal, Arnab Bhattacharya, and Sayan Ranu. 2021. GraphReach: Position-aware graph neural network using reachability estimations. In IJCAI.","journal-title":"IJCAI"},{"key":"e_1_3_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2008.01.039"},{"key":"e_1_3_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01205239"},{"key":"e_1_3_1_43_1","article-title":"Deepwalk: Online learning of social representations","author":"Perozzi Bryan","year":"2014","unstructured":"Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. 2014. Deepwalk: Online learning of social representations. In SIGKDD.","journal-title":"SIGKDD"},{"key":"e_1_3_1_44_1","article-title":"GREED: A neural framework for learning graph distance functions","author":"Ranjan Rishab","year":"2022","unstructured":"Rishab Ranjan, Siddharth Grover, Sourav Medya, Venkatesan Chakravarthy, Yogish Sabharwal, and Sayan Ranu. 2022. GREED: A neural framework for learning graph distance functions. In NeurIPS.","journal-title":"NeurIPS"},{"key":"e_1_3_1_45_1","article-title":"Beyond individualized recourse: Interpretable and interactive summaries of actionable recourses","author":"Rawal Kaivalya","year":"2020","unstructured":"Kaivalya Rawal and Himabindu Lakkaraju. 2020. Beyond individualized recourse: Interpretable and interactive summaries of actionable recourses. In NeurIPS.","journal-title":"NeurIPS"},{"key":"e_1_3_1_46_1","doi-asserted-by":"crossref","unstructured":"Kaspar Riesen and Horst Bunke. 2008. IAM graph database repository for graph based pattern recognition and machine learning. In SSPR & SPR. Springer 287\u2013297.","DOI":"10.1007\/978-3-540-89689-0_33"},{"key":"e_1_3_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"e_1_3_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313167"},{"issue":"3","key":"e_1_3_1_49_1","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/0014-5793(93)80557-B","article-title":"Peptide aldehydes as inhibitors of HIV protease","volume":"319","author":"Sarubbi Edoardo","year":"1993","unstructured":"Edoardo Sarubbi, Pier Fausto Seneci, Michael R. Angelastro, Norton P. Peet, Maurizio Denaro, and Khalid Islam. 1993. Peptide aldehydes as inhibitors of HIV protease. FEBS Letters 319, 3 (1993), 253\u2013256.","journal-title":"FEBS Letters"},{"issue":"9","key":"e_1_3_1_50_1","first-page":"2539","article-title":"Weisfeiler-lehman graph kernels","volume":"12","author":"Shervashidze Nino","year":"2011","unstructured":"Nino Shervashidze, Pascal Schweitzer, Erik Jan Van Leeuwen, Kurt Mehlhorn, and Karsten M. Borgwardt. 2011. Weisfeiler-lehman graph kernels. JMLR 12, 9 (2011), 2539\u20132561.","journal-title":"JMLR"},{"key":"e_1_3_1_51_1","unstructured":"Juntao Tan Shijie Geng Zuohui Fu Yingqiang Ge Shuyuan Xu Yunqi Li and Yongfeng Zhang. 2022. Learning and evaluating graph neural network explanations based on counterfactual and factual reasoning. In WebConf."},{"key":"e_1_3_1_52_1","article-title":"Unravelling the performance of physics-informed graph neural networks for dynamical systems","author":"Thangamuthu Abishek","year":"2022","unstructured":"Abishek Thangamuthu, Gunjan Kumar, Suresh Bishnoi, Ravinder Bhattoo, N. M. Anoop Krishnan, and Sayan Ranu. 2022. Unravelling the performance of physics-informed graph neural networks for dynamical systems. In NeurIPS.","journal-title":"NeurIPS"},{"key":"e_1_3_1_53_1","first-page":"16749","article-title":"Decisions, counterfactual explanations and strategic behavior","volume":"33","author":"Tsirtsis Stratis","year":"2020","unstructured":"Stratis Tsirtsis and Manuel Gomez Rodriguez. 2020. Decisions, counterfactual explanations and strategic behavior. In NeurIPS, Vol. 33, 16749\u201316760.","journal-title":"NeurIPS"},{"key":"e_1_3_1_54_1","first-page":"127","article-title":"Graph clustering with graph neural networks","volume":"24","author":"Tsitsulin Anton","year":"2023","unstructured":"Anton Tsitsulin, John Palowitch, Bryan Perozzi, and Emmanuel M\u00fcller. 2023. Graph clustering with graph neural networks. Journal of Machine Learning Research 24, 127 (2023), 1\u201321.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_1_55_1","article-title":"Actionable recourse in linear classification","author":"Ustun Berk","year":"2019","unstructured":"Berk Ustun, Alexander Spangher, and Yang Liu. 2019. Actionable recourse in linear classification. In FAT.","journal-title":"FAT"},{"key":"e_1_3_1_56_1","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107 Petar","year":"2018","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph attention networks. In ICLR.","journal-title":"ICLR"},{"key":"e_1_3_1_57_1","article-title":"InduCE: Inductive counterfactual explanations for graph neural networks","author":"Verma Samidha","year":"2024","unstructured":"Samidha Verma, Burouj Armgaan, Sourav Medya, and Sayan Ranu. 2024. InduCE: Inductive counterfactual explanations for graph neural networks. Transactions on Machine Learning Research (2024). Retrieved from https:\/\/openreview.net\/forum?id=RZPN8cgqST","journal-title":"Transactions on Machine Learning Research"},{"key":"e_1_3_1_58_1","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1007\/978-3-319-57959-7","volume-title":"The EU General Data Protection Regulation (GDPR). A Practical Guide","author":"Voigt Paul","year":"2017","unstructured":"Paul Voigt and Axel Von dem Bussche. 2017. The EU General Data Protection Regulation (GDPR). A Practical Guide (1st. ed.) Vol. 10, Springer International Publishing, 383 pages.","edition":"1"},{"key":"e_1_3_1_59_1","article-title":"PGM-Explainer: Probabilistic graphical model explanations for graph neural networks","author":"Vu Minh","year":"2020","unstructured":"Minh Vu and My T. Thai. 2020. PGM-Explainer: Probabilistic graphical model explanations for graph neural networks. In NeurIPS.","journal-title":"NeurIPS"},{"key":"e_1_3_1_60_1","first-page":"841","article-title":"Counterfactual explanations without opening the black box: Automated decisions and the GDPR","volume":"31","author":"Wachter Sandra","year":"2017","unstructured":"Sandra Wachter, Brent Mittelstadt, and Chris Russell. 2017. Counterfactual explanations without opening the black box: Automated decisions and the GDPR. Harvard Journal of Law & Technology 31 (2017), 841.","journal-title":"Harvard Journal of Law & Technology"},{"key":"e_1_3_1_61_1","article-title":"Comparison of descriptor spaces for chemical compound retrieval and classification","author":"Wale Nikil","year":"2006","unstructured":"Nikil Wale and George Karypis. 2006. Comparison of descriptor spaces for chemical compound retrieval and classification. In ICDM.","journal-title":"ICDM"},{"key":"e_1_3_1_62_1","first-page":"2991","volume-title":"KDD,","author":"Wang Danqing","year":"2024","unstructured":"Danqing Wang, Antonis Antoniades, Kha-Dinh Luong, Edwin Zhang, Mert Kosan, Jiachen Li, Ambuj Singh, William Yang Wang, and Lei Li. 2024. Global human-guided counterfactual explanations for molecular properties via reinforcement learning. In KDD, 2991\u20133000."},{"key":"e_1_3_1_63_1","article-title":"QGTC: Accelerating quantized graph neural networks via GPU tensor core","author":"Wang Yuke","year":"2022","unstructured":"Yuke Wang, Boyuan Feng, and Yufei Ding. 2022. QGTC: Accelerating quantized graph neural networks via GPU tensor core. In PPoPP.","journal-title":"PPoPP"},{"key":"e_1_3_1_64_1","article-title":"GNNAdvisor: An efficient runtime system for GNN acceleration on GPUs","author":"Wang Yuke","year":"2021","unstructured":"Yuke Wang, Boyuan Feng, Gushu Li, Shuangchen Li, Lei Deng, Yuan Xie, and Yufei Ding. 2021. GNNAdvisor: An efficient runtime system for GNN acceleration on GPUs. In OSDI.","journal-title":"OSDI"},{"key":"e_1_3_1_65_1","article-title":"End to end learning and optimization on graphs","author":"Wilder Bryan","year":"2019","unstructured":"Bryan Wilder, Eric Ewing, Bistra Dilkina, and Milind Tambe. 2019. End to end learning and optimization on graphs. In NeurIPS.","journal-title":"NeurIPS"},{"key":"e_1_3_1_66_1","article-title":"Task-agnostic graph explanations","author":"Xie Yaochen","year":"2022","unstructured":"Yaochen Xie, Sumeet Katariya, Xianfeng Tang, Edward Huang, Nikhil Rao, Karthik Subbian, and Shuiwang Ji. 2022. Task-agnostic graph explanations. In NeurIPS.","journal-title":"NeurIPS"},{"key":"e_1_3_1_67_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2021.02.011"},{"key":"e_1_3_1_68_1","article-title":"Like like alike: Joint friendship and interest propagation in social networks","author":"Yang Shuang-Hong","year":"2011","unstructured":"Shuang-Hong Yang, Bo Long, Alex Smola, Narayanan Sadagopan, Zhaohui Zheng, and Hongyuan Zha. 2011. Like like alike: Joint friendship and interest propagation in social networks. In WebConf.","journal-title":"WebConf"},{"key":"e_1_3_1_69_1","article-title":"GNNExplainer: Generating explanations for graph neural networks","author":"Ying Rex","year":"2019","unstructured":"Rex Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, and Jure Leskovec. 2019. GNNExplainer: Generating explanations for graph neural networks. In NeurIPS.","journal-title":"NeurIPS"},{"key":"e_1_3_1_70_1","article-title":"XGNN: Towards model-level explanations of graph neural networks","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 SIGKDD.","journal-title":"SIGKDD"},{"key":"e_1_3_1_71_1","first-page":"12241","article-title":"On explainability of graph neural networks via subgraph explorations","author":"Yuan Hao","year":"2021","unstructured":"Hao Yuan, Haiyang Yu, Jie Wang, Kang Li, and Shuiwang Ji. 2021. On explainability of graph neural networks via subgraph explorations. In ICML. PMLR, 12241\u201312252.","journal-title":"ICML"},{"key":"e_1_3_1_72_1","article-title":"Learning from counterfactual links for link prediction","author":"Zhao Tong","year":"2022","unstructured":"Tong Zhao, Gang Liu, Daheng Wang, Wenhao Yu, and Meng Jiang. 2022. Learning from counterfactual links for link prediction. In ICML.","journal-title":"ICML"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3698108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T01:59:14Z","timestamp":1755568754000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698108"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,18]]},"references-count":71,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10,31]]}},"alternative-id":["10.1145\/3698108"],"URL":"https:\/\/doi.org\/10.1145\/3698108","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,18]]},"assertion":[{"value":"2023-12-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-09-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}