{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T02:04:52Z","timestamp":1777341892965,"version":"3.51.4"},"reference-count":61,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T00:00:00Z","timestamp":1735171200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2025,2,28]]},"abstract":"<jats:p>\n            Nowadays, research into personalization has been focusing on explainability and fairness. Several approaches proposed in recent works are able to explain individual recommendations in a post-hoc manner or by explanation paths. However, explainability techniques applied to unfairness in recommendation have been limited to finding user\/item features mostly related to biased recommendations. In this article, we devised a novel algorithm that leverages counterfactuality methods to discover user unfairness explanations in the form of user-item interactions. In our counterfactual framework, interactions are represented as edges in a bipartite graph, with users and items as nodes. Our bipartite graph explainer perturbs the topological structure to find an altered version that minimizes the disparity in utility between the protected and unprotected demographic groups. Experiments on four real-world graphs coming from various domains showed that our method can systematically explain user unfairness on three state-of-the-art GNN-based recommendation models. Moreover, an empirical evaluation of the perturbed network uncovered relevant patterns that justify the nature of the unfairness discovered by the generated explanations. The source code and the preprocessed data sets are available at\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/jackmedda\/RS-BGExplainer\">https:\/\/github.com\/jackmedda\/RS-BGExplainer<\/jats:ext-link>\n            .\n          <\/jats:p>\n          <jats:p\/>","DOI":"10.1145\/3655631","type":"journal-article","created":{"date-parts":[[2024,4,3]],"date-time":"2024-04-03T12:08:46Z","timestamp":1712146126000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["GNNUERS: Fairness Explanation in GNNs for Recommendation via Counterfactual Reasoning"],"prefix":"10.1145","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1300-1876","authenticated-orcid":false,"given":"Giacomo","family":"Medda","sequence":"first","affiliation":[{"name":"University of Cagliari, Cagliari, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9631-1799","authenticated-orcid":false,"given":"Francesco","family":"Fabbri","sequence":"additional","affiliation":[{"name":"Spotify AB, Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1989-6057","authenticated-orcid":false,"given":"Mirko","family":"Marras","sequence":"additional","affiliation":[{"name":"University of Cagliari, Cagliari, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6053-3015","authenticated-orcid":false,"given":"Ludovico","family":"Boratto","sequence":"additional","affiliation":[{"name":"University of Cagliari, Cagliari, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4668-2476","authenticated-orcid":false,"given":"Gianni","family":"Fenu","sequence":"additional","affiliation":[{"name":"Universita degli Studi di Cagliari, Cagliari, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,12,26]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72357-6"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102646"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532041"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-99736-6_37"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2022.102021"},{"key":"e_1_3_2_7_2","first-page":"202","volume-title":"Proceedings of the Conference on Fairness, Accountability and Transparency","author":"Burke Robin","year":"2018","unstructured":"Robin Burke, Nasim Sonboli, and Aldo Ordonez-Gauger. 2018. Balanced neighborhoods for multi-sided fairness in recommendation. In Proceedings of the Conference on Fairness, Accountability and Transparency. PMLR, 202\u2013214.Retrieved from http:\/\/proceedings.mlr.press\/v81\/burke18a.html"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-13287-2"},{"key":"e_1_3_2_9_2","article-title":"CatGCN: Graph convolutional networks with categorical node features","author":"Chen Weijian","year":"2023","unstructured":"Weijian Chen, Fuli Feng, Qifan Wang, Xiangnan He, Chonggang Song, Guohui Ling, and Yongdong Zhang. 2023. CatGCN: Graph convolutional networks with categorical node features. IEEE Transactions on Knowledge and Data Engineering 35, 4 (2023), 3500\u20133511.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.5555\/3367243.3367333"},{"key":"e_1_3_2_11_2","unstructured":"Xu Chen Yongfeng Zhang and Ji-Rong Wen. 2022. Measuring \u201cwhy\u201d in recommender systems: A comprehensive survey on the evaluation of explainable recommendation. arXiv:2202.06466. Retrieved from https:\/\/arxiv.org\/abs\/2202.06466"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Ziheng Chen Fabrizio Silvestri Jia Wang Yongfeng Zhang Zhenhua Huang Hongshik Ahn and Gabriele Tolomei. 2022. GREASE: Generate factual and counterfactual explanations for GNN-based recommendations. arXiv:2208.04222. Retrieved from 10.48550\/arXiv.2208.04222","DOI":"10.48550\/arXiv.2208.04222"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-99739-7_9"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102662"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25905"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1561\/1500000079"},{"key":"e_1_3_2_17_2","first-page":"172","volume-title":"Proceedings of the Conference on Fairness, Accountability and Transparency","author":"Ekstrand Michael D.","year":"2018","unstructured":"Michael D. Ekstrand, Mucun Tian, Ion Madrazo Azpiazu, Jennifer D. Ekstrand, Oghenemaro Anuyah, David McNeill, and Maria Soledad Pera. 2018. All the cool kids, how do they fit in?: Popularity and demographic biases in recommender evaluation and effectiveness. In Proceedings of the Conference on Fairness, Accountability and Transparency. PMLR, 172\u2013186. Retrieved from http:\/\/proceedings.mlr.press\/v81\/ekstrand18b.html"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v16i1.19284"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.15439\/2021F117"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531973"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371824"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449848"},{"key":"e_1_3_2_23_2","unstructured":"William L. Hamilton Rex Ying and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS\u201917). Curran Associates Inc. Red Hook NY USA 1025\u20131035."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/2827872"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570376"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"e_1_3_2_28_2","first-page":"187","volume-title":"Proceedings of the Conference on Fairness, Accountability and Transparency","author":"Kamishima Toshihiro","year":"2018","unstructured":"Toshihiro Kamishima, Shotaro Akaho, Hideki Asoh, and Jun Sakuma. 2018. Recommendation independence. In Proceedings of the Conference on Fairness, Accountability and Transparency. PMLR, 187\u2013201."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-93736-2_36"},{"key":"e_1_3_2_30_2","volume-title":"5th International Conference on Learning Representations, Conference Track Proceedings","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In 5th International Conference on Learning Representations, Conference Track Proceedings."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449866"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462966"},{"key":"e_1_3_2_33_2","first-page":"4499","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","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 International Conference on Artificial Intelligence and Statistics. PMLR, 4499\u20134511."},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498391"},{"key":"e_1_3_2_35_2","volume-title":"Proceedings of the Workshop on Recommendation in Multi-stakeholder Environments Co-located with the 13th ACM Conference on Recommender Systems.","author":"Mansoury Masoud","year":"2019","unstructured":"Masoud Mansoury, Bamshad Mobasher, Robin Burke, and Mykola Pechenizkiy. 2019. Bias disparity in collaborative recommendation: Algorithmic evaluation and comparison. In Proceedings of the Workshop on Recommendation in Multi-stakeholder Environments Co-located with the 13th ACM Conference on Recommender Systems.CEUR-WS.org."},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3457607"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.67.026126"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557425"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-009-9124-x"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531718"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220088"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.61"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482420"},{"key":"e_1_3_2_44_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_45_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Veli\u010dkovi\u0107 Petar","year":"2017","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2017. Graph attention networks. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512189"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","unstructured":"Nan Wang Qifan Wang Yi-Chia Wang Maziar Sanjabi Jingzhou Liu Hamed Firooz Hongning Wang and Shaoliang Nie. 2023. COFFEE: Counterfactual fairness for personalized text generation in explainable recommendation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP\u201923) Houda Bouamor Juan Pino and Kalika Bali (Eds.). Association for Computational Linguistics 13258\u201313275. 10.18653\/V1\/2023.EMNLP-MAIN.819","DOI":"10.18653\/V1\/2023.EMNLP-MAIN.819"},{"key":"e_1_3_2_48_2","article-title":"Trustworthy recommender systems","volume":"2208","author":"Wang Shoujin","year":"2022","unstructured":"Shoujin Wang, Xiuzhen Zhang, Yan Wang, Huan Liu, and Francesco Ricci. 2022. Trustworthy recommender systems. CoRR abs\/2208.06265 (2022).","journal-title":"CoRR"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331267"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3547333"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16573"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3564285"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482170"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017370"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403085"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204236"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583511"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1561\/1500000066"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981333"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482016"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477314.3507029"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3655631","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3655631","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:46Z","timestamp":1750291426000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3655631"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,26]]},"references-count":61,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,2,28]]}},"alternative-id":["10.1145\/3655631"],"URL":"https:\/\/doi.org\/10.1145\/3655631","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,26]]},"assertion":[{"value":"2023-06-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-19","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}