{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:46:43Z","timestamp":1781797603653,"version":"3.54.5"},"reference-count":83,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"name":"National Recovery and Resilience Plan funded by the European Union NextGenerationEU","award":["PE00000014 (SERICS), and PE0000013 (FAIR), IR0000013 (SoBigData.it)"],"award-info":[{"award-number":["PE00000014 (SERICS), and PE0000013 (FAIR), IR0000013 (SoBigData.it)"]}]},{"name":"Italian Ministry of University and Research under the PRIN 2022 program","award":["2022Y34XNM (HyperKG \u2013\u2013 Hybrid Prediction and Explanation with Knowledge Graphs), 2022AEFHA (NEREO \u2013\u2013 Neural Reasoning Over Open Data)"],"award-info":[{"award-number":["2022Y34XNM (HyperKG \u2013\u2013 Hybrid Prediction and Explanation with Knowledge Graphs), 2022AEFHA (NEREO \u2013\u2013 Neural Reasoning Over Open Data)"]}]},{"name":"Sapienza University of Rome - \u201cProgetti di Ricerca Grandi\u201d","award":["RG124190FD55EB57 (GHOST \u2013\u2013 Protecting User Privacy from Community Detection in Social Networks), and RD12318A97C04F22 (SEEDS \u2013\u2013 Sustainable Ecosystems in Evolving Digital Societies)"],"award-info":[{"award-number":["RG124190FD55EB57 (GHOST \u2013\u2013 Protecting User Privacy from Community Detection in Social Networks), and RD12318A97C04F22 (SEEDS \u2013\u2013 Sustainable Ecosystems in Evolving Digital Societies)"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Recomm. Syst."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>\n                    Recently, graph neural networks (GNNs) have become the new state-of-the-art approach to developing powerful recommender systems. However, it is hard for GNN-based recommender systems to attach tangible explanations of why a specific item ends up in the list of top-\n                    <jats:italic toggle=\"yes\">k<\/jats:italic>\n                    suggestions for a given user. Indeed, explaining GNN-based recommendations is unique, and existing GNN explanation methods are inappropriate since they are designed to explain node, edge, or graph classification rather than ranking.\n                  <\/jats:p>\n                  <jats:p>\n                    In this work, we propose GREASE, a novel method for explaining the list of top-\n                    <jats:italic toggle=\"yes\">k<\/jats:italic>\n                    suggested items to a given user provided by any black-box GNN-based recommender system. Specifically, for each recommended item, GREASE first trains a surrogate GNN model on the subgraph obtained as the union of the target user-item pair and its\n                    <jats:italic toggle=\"yes\">l<\/jats:italic>\n                    -hop neighborhood. Then, it\n                    <jats:italic toggle=\"yes\">jointly<\/jats:italic>\n                    generates factual and counterfactual explanations by finding optimal adjacency matrix perturbations to capture the\n                    <jats:italic toggle=\"yes\">sufficient<\/jats:italic>\n                    and\n                    <jats:italic toggle=\"yes\">necessary<\/jats:italic>\n                    conditions for the item to be recommended. Experiments on real-world datasets show that GREASE can generate concise and compelling explanations for popular GNN-based recommender models.\n                  <\/jats:p>\n                  <jats:p\/>","DOI":"10.1145\/3731683","type":"journal-article","created":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T07:28:43Z","timestamp":1747121323000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Joint Factual and Counterfactual Explanations for Top-k GNN-based Recommendations"],"prefix":"10.1145","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2585-637X","authenticated-orcid":false,"given":"Ziheng","family":"Chen","sequence":"first","affiliation":[{"name":"Stony Brook University","place":["Stony Brook, United States"]},{"name":"Walmart Global Tech","place":["Stony Brook, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6063-3545","authenticated-orcid":false,"given":"Jin","family":"Huang","sequence":"additional","affiliation":[{"name":"Stony Brook University","place":["Stony Brook, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7669-9055","authenticated-orcid":false,"given":"Fabrizio","family":"Silvestri","sequence":"additional","affiliation":[{"name":"University of Rome La Sapienza","place":["Rome, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2633-8555","authenticated-orcid":false,"given":"Yongfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Rutgers University","place":["New Brunswick, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8924-6159","authenticated-orcid":false,"given":"Hongshik","family":"Ahn","sequence":"additional","affiliation":[{"name":"Stony Brook University","place":["Stony Brook, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7471-6659","authenticated-orcid":false,"given":"Gabriele","family":"Tolomei","sequence":"additional","affiliation":[{"name":"University of Rome La Sapienza","place":["Rome, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,22]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"2018. Yelp Dataset. [Online]. Retrieved from https:\/\/github.com\/gusye1234\/LightGCN-PyTorch\/tree\/master\/data\/yelp2018\/"},{"key":"e_1_3_2_3_2","unstructured":"2020. LastFM Dataset. [Online]. Retrieved from https:\/\/github.com\/gusye1234\/LightGCN-PyTorch\/blob\/master\/data\/lastfm\/"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/245108.245124"},{"key":"e_1_3_2_5_2","unstructured":"Federico Baldassarre and Hossein Azizpour. 2019. Explainability techniques for graph convolutional networks. arXiv:1905.13686. Retrieved from https:\/\/arxiv.org\/abs\/1905.13686"},{"key":"e_1_3_2_6_2","unstructured":"Rianne van den Berg Thomas N. Kipf and Max Welling. 2017. Graph convolutional matrix completion. arXiv:1706.02263. Retrieved from https:\/\/arxiv.org\/abs\/1706.02263"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1021240730564"},{"key":"e_1_3_2_8_2","first-page":"1583","volume-title":"Proceedings of the WebConf\u201918","author":"Chen Chong","year":"2018","unstructured":"Chong Chen, Min Zhang, Yiqun Liu, and Shaoping Ma. 2018. Neural attentional rating regression with review-level explanations. In Proceedings of the WebConf\u201918. 1583\u20131592."},{"key":"e_1_3_2_9_2","first-page":"75","volume-title":"Proceedings of the WSDM\u201922","author":"Chen Hanxiong","year":"2022","unstructured":"Hanxiong Chen, Yunqi Li, Shaoyun Shi, Shuchang Liu, He Zhu, and Yongfeng Zhang. 2022. Graph collaborative reasoning. In Proceedings of the WSDM\u201922. ACM, 75\u201384."},{"key":"e_1_3_2_10_2","first-page":"1516","volume-title":"Proceedings of the WWW\u201921","author":"Chen Hanxiong","year":"2021","unstructured":"Hanxiong Chen, Shaoyun Shi, Yunqi Li, and Yongfeng Zhang. 2021. Neural collaborative reasoning. In Proceedings of the WWW\u201921. ACM, 1516\u20131527."},{"key":"e_1_3_2_11_2","first-page":"27","volume-title":"Proceedings of the AAAI\u201920","author":"Chen Lei","year":"2020","unstructured":"Lei Chen, Le Wu, Richang Hong, Kun Zhang, and Meng Wang. 2020. Revisiting graph based collaborative filtering: A linear residual graph convolutional network approach. In Proceedings of the AAAI\u201920. AAAI Press, 27\u201334."},{"key":"e_1_3_2_12_2","first-page":"765","volume-title":"Proceedings of the SIGIR\u201919","author":"Chen Xu","year":"2019","unstructured":"Xu Chen, Hanxiong Chen, Hongteng Xu, Yongfeng Zhang, Yixin Cao, Zheng Qin, and Hongyuan Zha. 2019. Personalized fashion recommendation with visual explanations based on multimodal attention network: Towards visually explainable recommendation. In Proceedings of the SIGIR\u201919. 765\u2013774."},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3223892"},{"key":"e_1_3_2_14_2","first-page":"252","volume-title":"Proceedings of the CIKM\u201922","author":"Chen Ziheng","year":"2022","unstructured":"Ziheng Chen, Fabrizio Silvestri, Jia Wang, He Zhu, Hongshik Ahn, and Gabriele Tolomei. 2022. ReLAX: Reinforcement learning agent explainer for arbitrary predictive models. In Proceedings of the CIKM\u201922. ACM, 252\u2013261."},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_16_2","first-page":"1082","volume-title":"Proceedings of the KDD\u201911","author":"Cho Eunjoon","year":"2011","unstructured":"Eunjoon Cho, Seth A. Myers, and Jure Leskovec. 2011. Friendship and mobility: User movement in location-based social networks. In Proceedings of the KDD\u201911. ACM, 1082\u20131090."},{"key":"e_1_3_2_17_2","first-page":"423","article-title":"Graph neural networks in modern recommender systems","author":"Chu Yunfei","year":"2022","unstructured":"Yunfei Chu, Jiangchao Yao, Chang Zhou, and Hongxia Yang. 2022. Graph neural networks in modern recommender systems. Graph Neural Networks: Foundations, Frontiers, and Applications (2022), 423\u2013445.","journal-title":"Graph Neural Networks: Foundations, Frontiers, and Applications"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0747-7171(08)80013-2"},{"key":"e_1_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Alexandre Duval and Fragkiskos D. Malliaros. 2021. GraphSVX: Shapley value explanations for graph neural networks. arXiv:2104.10482. Retrieved from https:\/\/arxiv.org\/abs\/2104.10482","DOI":"10.1007\/978-3-030-86520-7_19"},{"key":"e_1_3_2_20_2","first-page":"1623","volume-title":"Proceedings of the WSDM\u201922","author":"Gao Chen","year":"2022","unstructured":"Chen Gao, Xiang Wang, Xiangnan He, and Yong Li. 2022. Graph neural networks for recommender system. In Proceedings of the WSDM\u201922. ACM, 1623\u20131625."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","unstructured":"Azin Ghazimatin. 2021. Enhancing Explainability and Scrutability of Recommender Systems. DOI:10.22028\/D291-35516","DOI":"10.22028\/D291-35516"},{"key":"e_1_3_2_22_2","volume-title":"Causal Inference in Statistics: A Primer","author":"Glymour Madelyn","year":"2016","unstructured":"Madelyn Glymour, Judea Pearl, and Nicholas P. Jewell. 2016. Causal Inference in Statistics: A Primer. John Wiley and Sons."},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3236009"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/239"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01588-5"},{"key":"e_1_3_2_26_2","first-page":"1025","volume-title":"Proceedings of the NeurIPS\u201917","author":"Hamilton William L.","year":"2017","unstructured":"William L. Hamilton, Rex Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Proceedings of the NeurIPS\u201917. Curran Assoc. Inc., 1025\u20131035."},{"issue":"4","key":"e_1_3_2_27_2","first-page":"784","article-title":"Topic-sensitive PageRank: A context-sensitive ranking algorithm for web search","volume":"15","author":"Haveliwala Taher","year":"2003","unstructured":"Taher Haveliwala. 2003. Topic-sensitive PageRank: A context-sensitive ranking algorithm for web search. IEEE TKDE 15, 4 (2003), 784\u2013796.","journal-title":"IEEE TKDE"},{"key":"e_1_3_2_28_2","first-page":"355","volume-title":"Proceedings of the SIGIR\u201917","author":"He Xiangnan","year":"2017","unstructured":"Xiangnan He and Tat-Seng Chua. 2017. Neural factorization machines for sparse predictive analytics. In Proceedings of the SIGIR\u201917. ACM, 355\u2013364."},{"key":"e_1_3_2_29_2","first-page":"639","volume-title":"Proceedings of the SIGIR\u201920","author":"He Xiangnan","year":"2020","unstructured":"Xiangnan He, Kuan Deng, Xiang Wang, Yan Li, YongDong Zhang, and Meng Wang. 2020. LightGCN: Simplifying and powering graph convolution network for recommendation. In Proceedings of the SIGIR\u201920. ACM, 639\u2013648."},{"key":"e_1_3_2_30_2","first-page":"173","volume-title":"Proceedings of the WWW\u201917","author":"He Xiangnan","year":"2017","unstructured":"Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. 2017. Neural collaborative filtering. In Proceedings of the WWW\u201917. IW3C2, 173\u2013182."},{"key":"e_1_3_2_31_2","first-page":"4115","volume-title":"Proceedings of the AAAI\u201921","author":"Huang Chao","year":"2021","unstructured":"Chao Huang, Huance Xu, Yong Xu, Peng Dai, Lianghao Xia, Mengyin Lu, Liefeng Bo, Hao Xing, Xiaoping Lai, and Yanfang Ye. 2021. Knowledge-aware coupled graph neural network for social recommendation. In Proceedings of the AAAI\u201921. 4115\u20134122."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599768"},{"key":"e_1_3_2_33_2","first-page":"895","volume-title":"Proceedings of the AISTATS\u201920","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 Proceedings of the AISTATS\u201920. PMLR, 895\u2013905."},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_35_2","first-page":"238","volume-title":"Proceedings of the KDD\u201920","author":"Le Thai","year":"2020","unstructured":"Thai Le, Suhang Wang, and Dongwon Lee. 2020. GRACE: Generating concise and informative contrastive sample to explain neural network model\u2019s prediction. In Proceedings of the KDD\u201920. ACM, 238\u2013248."},{"key":"e_1_3_2_36_2","first-page":"296","volume-title":"Proceedings of the ISSAC\u201914","author":"Gall Fran\u00e7ois Le","year":"2014","unstructured":"Fran\u00e7ois Le Gall. 2014. Powers of tensors and fast matrix multiplication. In Proceedings of the ISSAC\u201914. ACM, 296\u2013303."},{"key":"e_1_3_2_37_2","first-page":"304","volume-title":"Proceedings of the WSDM\u201920","author":"Lei Wenqiang","year":"2020","unstructured":"Wenqiang Lei, Xiangnan He, Yisong Miao, Qingyun Wu, Richang Hong, Min-Yen Kan, and Tat-Seng Chua. 2020. Estimation-action-reflection: Towards deep interaction between conversational and recommender systems. In Proceedings of the WSDM\u201920. ACM, 304\u2013312."},{"key":"e_1_3_2_38_2","first-page":"2873","volume-title":"Proceedings of the IJCAI\u201919","author":"Li Chong","year":"2019","unstructured":"Chong Li, Kunyang Jia, Dan Shen, C. J. Richard Shi, and Hongxia Yang. 2019. Hierarchical representation learning for bipartite graphs. In Proceedings of the IJCAI\u201919. AAAI Press, 2873\u20132879."},{"key":"e_1_3_2_39_2","first-page":"1017","volume-title":"Proceedings of the ICDE\u201922","author":"Li Haoyang","year":"2022","unstructured":"Haoyang Li, Shimin Di, Zijian Li, Lei Chen, and Jiannong Cao. 2022. Black-box adversarial attack and defense on graph neural networks. In Proceedings of the ICDE\u201922. IEEE, 1017\u20131030."},{"key":"e_1_3_2_40_2","first-page":"755","volume-title":"Proceedings of the CIKM\u201920","author":"Li Lei","year":"2020","unstructured":"Lei Li, Yongfeng Zhang, and Li Chen. 2020. Generate neural template explanations for recommendation. In Proceedings of the CIKM\u201920. 755\u2013764."},{"key":"e_1_3_2_41_2","unstructured":"Wanyu Lin Hao Lan and Baochun Li. 2021. Generative causal explanations for graph neural networks. arXiv:2104.06643. Retrieved from https:\/\/arxiv.org\/abs\/2104.06643"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512104"},{"key":"e_1_3_2_43_2","unstructured":"Zhiwei Liu Lin Meng Fei Jiang Jiawei Zhang and Philip S. Yu. 2020. Deoscillated graph collaborative filtering. arXiv:2011.02100. Retrieved from https:\/\/arxiv.org\/abs\/2011.02100"},{"key":"e_1_3_2_44_2","first-page":"5313","volume-title":"Proceedings of the AAAI\u201922","author":"Lucic Ana","year":"2022","unstructured":"Ana Lucic, Harrie Oosterhuis, Hinda Haned, and Maarten de Rijke. 2022. FOCUS: Flexible optimizable counterfactual explanations for tree ensembles. In Proceedings of the AAAI\u201922. AAAI, 5313\u20135322."},{"key":"e_1_3_2_45_2","first-page":"4499","volume-title":"Proceedings of the AISTATS\u201922","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 Proceedings of the AISTATS\u201922. PMLR, 4499\u20134511."},{"key":"e_1_3_2_46_2","first-page":"4765","volume-title":"Proceedings of the NeurIPS\u201917","author":"Lundberg Scott M.","year":"2017","unstructured":"Scott M. Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Proceedings of the NeurIPS\u201917. Curran Associates, Inc., 4765\u20134774."},{"key":"e_1_3_2_47_2","first-page":"19620","volume-title":"Proceedings of the NeurIPS\u201920","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 Proceedings of the NeurIPS\u201920. Curran Associates Inc., 19620\u201319631."},{"key":"e_1_3_2_48_2","first-page":"607","volume-title":"Proceedings of the FAT*\u201920","author":"Mothilal Ramaravind Kommiya","year":"2020","unstructured":"Ramaravind Kommiya Mothilal, Amit Sharma, and Chenhao Tan. 2020. Explaining machine learning classifiers through diverse counterfactual explanations. In Proceedings of the FAT*\u201920. ACM, 607\u2013617."},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3496616"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72079-9_10"},{"key":"e_1_3_2_51_2","first-page":"10764","volume-title":"Proceedings of the CVPR\u201919","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 Proceedings of the CVPR\u201919. IEEE, 10764\u201310773."},{"key":"e_1_3_2_52_2","first-page":"995","volume-title":"Proceedings of the ICDM\u201910","author":"Rendle Steffen","year":"2010","unstructured":"Steffen Rendle. 2010. Factorization machines. In Proceedings of the ICDM\u201910. IEEE, 995\u20131000."},{"key":"e_1_3_2_53_2","first-page":"1135","volume-title":"Proceedings of the KDD\u201916","author":"Ribeiro Marco Tulio","year":"2016","unstructured":"Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. \u201cWhy Should I Trust You?\u201d: Explaining the predictions of any classifier. In Proceedings of the KDD\u201916. ACM, 1135\u20131144."},{"key":"e_1_3_2_54_2","first-page":"285","volume-title":"Proceedings of the WWW\u201901","author":"Sarwar Badrul","year":"2001","unstructured":"Badrul Sarwar, George Karypis, Joseph Konstan, and John Riedl. 2001. Item-based collaborative filtering recommendation algorithms. In Proceedings of the WWW\u201901. IW3C2, 285\u2013295."},{"key":"e_1_3_2_55_2","first-page":"291","volume-title":"Collaborative Filtering Recommender Systems","author":"Schafer J. Ben","year":"2007","unstructured":"J. Ben Schafer, Dan Frankowski, Jon Herlocker, and Shilad Sen. 2007. Collaborative Filtering Recommender Systems. Springer, 291\u2013324."},{"key":"e_1_3_2_56_2","first-page":"593","volume-title":"Proceedings of the ESWC\u201918","author":"Schlichtkrull Michael","year":"2018","unstructured":"Michael Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, and Max Welling. 2018. Modeling relational data with graph convolutional networks. In Proceedings of the ESWC\u201918. Springer, 593\u2013607."},{"key":"e_1_3_2_57_2","unstructured":"Michael Sejr Schlichtkrull Nicola De Cao and Ivan Titov. 2020. Interpreting graph neural networks for NLP with differentiable edge masking. arXiv:2010.00577. Retrieved from https:\/\/arxiv.org\/abs\/2010.00577"},{"key":"e_1_3_2_58_2","first-page":"1","volume-title":"Proceedings of the IJCNN\u201922","author":"Siciliano Federico","year":"2022","unstructured":"Federico Siciliano, Maria Sofia Bucarelli, Gabriele Tolomei, and Fabrizio Silvestri. 2022. NEWRON: A new generalization of the artificial neuron to enhance the interpretability of neural networks. In Proceedings of the IJCNN\u201922. IEEE, 1\u201317."},{"key":"e_1_3_2_59_2","unstructured":"Karen Simonyan Andrea Vedaldi and Andrew Zisserman. 2013. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv:1312.6034. Retrieved from https:\/\/arxiv.org\/abs\/1312.6034"},{"key":"e_1_3_2_60_2","unstructured":"Daniel Smilkov Nikhil Thorat Been Kim Fernanda Vi\u00e9gas and Martin Wattenberg. 2017. Smoothgrad: Removing noise by adding noise. arXiv:1706.03825. Retrieved from https:\/\/arxiv.org\/abs\/1706.03825"},{"key":"e_1_3_2_61_2","first-page":"1289","volume-title":"Proceedings of the SIGIR\u201920","author":"Sun Jianing","year":"2020","unstructured":"Jianing Sun, Yingxue Zhang, Wei Guo, Huifeng Guo, Ruiming Tang, Xiuqiang He, Chen Ma, and Mark Coates. 2020. Neighbor interaction aware graph convolution networks for recommendation. In Proceedings of the SIGIR\u201920. ACM, 1289\u20131298."},{"key":"e_1_3_2_62_2","first-page":"1306","volume-title":"Proceedings of the ICDM\u201919","author":"Sun Jianing","year":"2019","unstructured":"Jianing Sun, Yingxue Zhang, Chen Ma, Mark Coates, Huifeng Guo, Ruiming Tang, and Xiuqiang He. 2019. Multi-graph convolution collaborative filtering. In Proceedings of the ICDM\u201919. IEEE, 1306\u20131311."},{"key":"e_1_3_2_63_2","first-page":"1018","volume-title":"Proceedings of the WWW\u201922","author":"Tan Juntao","year":"2022","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 Proceedings of the WWW\u201922. ACM, 1018\u20131027."},{"key":"e_1_3_2_64_2","first-page":"1784","volume-title":"Proceedings of the CIKM\u201921","author":"Tan Juntao","year":"2021","unstructured":"Juntao Tan, Shuyuan Xu, Yingqiang Ge, Yunqi Li, Xu Chen, and Yongfeng Zhang. 2021. Counterfactual explainable recommendation. In Proceedings of the CIKM\u201921. ACM, 1784\u20131793."},{"key":"e_1_3_2_65_2","doi-asserted-by":"crossref","unstructured":"Thiviyan Thanapalasingam Lucas van Berkel Peter Bloem and Paul Groth. 2021. Relational graph convolutional networks: A closer look. arXiv:2107.10015. Retrieved from https:\/\/arxiv.org\/abs\/2107.10015","DOI":"10.7717\/peerj-cs.1073"},{"issue":"4","key":"e_1_3_2_66_2","first-page":"1540","article-title":"Generating actionable interpretations from ensembles of decision trees","volume":"33","author":"Tolomei Gabriele","year":"2021","unstructured":"Gabriele Tolomei and Fabrizio Silvestri. 2021. Generating actionable interpretations from ensembles of decision trees. IEEE TKDE 33, 4 (2021), 1540\u20131553.","journal-title":"IEEE TKDE"},{"key":"e_1_3_2_67_2","first-page":"465","volume-title":"Proceedings of the KDD\u201917","author":"Tolomei Gabriele","year":"2017","unstructured":"Gabriele Tolomei, Fabrizio Silvestri, Andrew Haines, and Mounia Lalmas. 2017. Interpretable predictions of tree-based ensembles via actionable feature tweaking. In Proceedings of the KDD\u201917. ACM, 465\u2013474."},{"key":"e_1_3_2_68_2","first-page":"1627","volume-title":"Proceedings of the SIGIR\u201921","author":"Tran Khanh Hiep","year":"2021","unstructured":"Khanh Hiep Tran, Azin Ghazimatin, and Rishiraj Saha Roy. 2021. Counterfactual explanations for neural recommenders. In Proceedings of the SIGIR\u201921. ACM, 1627\u20131631."},{"key":"e_1_3_2_69_2","article-title":"Attention is all you need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems 30 (2017).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_70_2","first-page":"12225","volume-title":"Proceedings of the NeurIPS\u201920","author":"Vu Minh N.","year":"2020","unstructured":"Minh N. Vu and My T. Thai. 2020. PGM-Explainer: Probabilistic graphical model explanations for graph neural networks. In Proceedings of the NeurIPS\u201920. 12225\u201312235."},{"key":"e_1_3_2_71_2","first-page":"165","volume-title":"Proceedings of the SIGIR\u201919","author":"Wang Xiang","year":"2019","unstructured":"Xiang Wang, Xiangnan He, Meng Wang, Fuli Feng, and Tat-Seng Chua. 2019. Neural graph collaborative filtering. In Proceedings of the SIGIR\u201919. ACM, 165\u2013174."},{"key":"e_1_3_2_72_2","first-page":"4753","article-title":"DiffNet++: A neural influence and interest diffusion network for social recommendation","volume":"34","author":"Wu Le","year":"2020","unstructured":"Le Wu, Junwei Li, Peijie Sun, Richang Hong, Yong Ge, and Meng Wang. 2020. DiffNet++: A neural influence and interest diffusion network for social recommendation. IEEE TKDE 34, 10 (2020), 4753\u20134766.","journal-title":"IEEE TKDE"},{"key":"e_1_3_2_73_2","first-page":"679","volume-title":"Proceedings of the SIGIR\u201920","author":"Wu Le","year":"2020","unstructured":"Le Wu, Yonghui Yang, Kun Zhang, Richang Hong, Yanjie Fu, and Meng Wang. 2020. Joint item recommendation and attribute inference: An adaptive graph convolutional network approach. In Proceedings of the SIGIR\u201920. ACM, 679\u2013688."},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3535101"},{"key":"e_1_3_2_75_2","first-page":"3600","volume-title":"Proceedings of the WebConf\u201919","author":"Yang Fan","year":"2019","unstructured":"Fan Yang, Shiva K. Pentyala, Sina Mohseni, Mengnan Du, Hao Yuan, Rhema Linder, Eric D Ragan, Shuiwang Ji, and Xia Hu. 2019. Xfake: Explainable fake news detector with visualizations. In Proceedings of the WebConf\u201919. 3600\u20133604."},{"key":"e_1_3_2_76_2","unstructured":"Rex Ying Dylan Bourgeois Jiaxuan You Marinka Zitnik and Jure Leskovec. 2019. GNNExplainer: Generating explanations for graph neural networks. arXiv:1903.03894. Retrieved from https:\/\/arxiv.org\/abs\/1903.03894"},{"key":"e_1_3_2_77_2","first-page":"974","volume-title":"Proceedings of the KDD\u201918","author":"Ying Rex","year":"2018","unstructured":"Rex Ying, Ruining He, Kaifeng Chen, Pong Eksombatchai, William L. Hamilton, and Jure Leskovec. 2018. Graph convolutional neural networks for web-scale recommender systems. In Proceedings of the KDD\u201918. ACM, 974\u2013983."},{"key":"e_1_3_2_78_2","article-title":"GNNExplainer: Generating explanations for graph neural networks","volume":"32","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. Advances in Neural Information Processing Systems 32 (2019).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_79_2","unstructured":"Hao Yuan Haiyang Yu Shurui Gui and Shuiwang Ji. 2020. Explainability in graph neural networks: A taxonomic survey. arXiv:2012.15445. Retrieved from https:\/\/arxiv.org\/abs\/2012.15445"},{"key":"e_1_3_2_80_2","first-page":"12241","volume-title":"Proceedings of the ICML\u201921","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 Proceedings of the ICML\u201921. PMLR, 12241\u201312252."},{"key":"e_1_3_2_81_2","first-page":"3784","volume-title":"Proceedings of the Web Conference\u201923","author":"Zhang Shichang","year":"2023","unstructured":"Shichang Zhang, Jiani Zhang, Xiang Song, Soji Adeshina, Da Zheng, Christos Faloutsos, and Yizhou Sun. 2023. PaGE-Link: Path-based graph neural network explanation for heterogeneous link prediction. In Proceedings of the Web Conference\u201923. ACM, 3784\u20133793."},{"key":"e_1_3_2_82_2","first-page":"3229","volume-title":"Proceedings of the WWW\u201922","author":"Zhang Wei","year":"2022","unstructured":"Wei Zhang, Junbing Yan, Zhuo Wang, and Jianyong Wang. 2022. Neuro-symbolic interpretable collaborative filtering for attribute-based recommendation. In Proceedings of the WWW\u201922. ACM, 3229\u20133238."},{"key":"e_1_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.1561\/1500000066"},{"key":"e_1_3_2_84_2","first-page":"2921","volume-title":"Proceedings of the CVPR\u201916","author":"Zhou Bolei","year":"2016","unstructured":"Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. 2016. Learning deep features for discriminative localization. In Proceedings of the CVPR\u201916. IEEE, 2921\u20132929."}],"container-title":["ACM Transactions on Recommender Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731683","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T16:50:36Z","timestamp":1763830236000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731683"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,22]]},"references-count":83,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3731683"],"URL":"https:\/\/doi.org\/10.1145\/3731683","relation":{},"ISSN":["2770-6699"],"issn-type":[{"value":"2770-6699","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,22]]},"assertion":[{"value":"2024-06-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}