{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T00:49:17Z","timestamp":1772498957366,"version":"3.50.1"},"reference-count":35,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100008431","name":"Regional Ministry of Education of the Junta de Castilla y Le\u00f3n (Spain)","doi-asserted-by":"publisher","award":["SA061G24"],"award-info":[{"award-number":["SA061G24"]}],"id":[{"id":"10.13039\/501100008431","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>Bias in artificial intelligence is a critical issue because these technologies increasingly influence decision-making in a wide range of areas. The recommender system field is one of them, where biases can lead to unfair or skewed outcomes. The origin usually lies in data biases coming from historical inequalities or irregular sampling. Recommendation algorithms using such data contribute to a greater or lesser extent to amplify and perpetuate those imbalances. On the other hand, different types of biases can be found in the outputs of recommender systems, and they can be evaluated by a variety of metrics specific to each of them. However, biases should not be treated independently, as they are interrelated and can potentiate or mask each other. Properly assessing the biases is crucial for ensuring fair and equitable recommendations. This work focuses on analyzing the interrelationship between different types of biases and proposes metrics designed to jointly evaluate multiple interrelated biases, with particular emphasis on those biases that tend to mask or obscure discriminatory treatment against minority or protected demographic groups, evaluated in terms of disparities in recommendation quality outcomes. This approach enables a more comprehensive assessment of algorithmic performance in terms of both fairness and predictive accuracy. Special attention is given to Graph Neural Network-based recommender systems, due to their strong performance in this application domain.<\/jats:p>","DOI":"10.3390\/fi17100461","type":"journal-article","created":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T12:04:52Z","timestamp":1759925092000},"page":"461","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Measuring Inter-Bias Effects and Fairness-Accuracy Trade-Offs in GNN-Based Recommender Systems"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7300-6126","authenticated-orcid":false,"given":"Nikzad","family":"Chizari","sequence":"first","affiliation":[{"name":"Department of Computer Science and Automation, University of Salamanca, 37008 Salamanca, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7624-5328","authenticated-orcid":false,"given":"Keywan","family":"Tajfar","sequence":"additional","affiliation":[{"name":"Department of Statistics, University of Tehran, Tehran 1417614411, Iran"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2809-3707","authenticated-orcid":false,"given":"Mar\u00eda","family":"Moreno-Garc\u00eda","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Automation, University of Salamanca, 37008 Salamanca, Spain"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Fahse, T., Huber, V., and Giffen, B.V. (2021, January 9\u201311). Managing Bias in Machine Learning Projects. Proceedings of the International Conference on Wirtschaftsinformatik, Essen, Germany.","DOI":"10.1007\/978-3-030-86797-3_7"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1080\/0960085X.2021.1927212","article-title":"Algorithmic Bias: Review, Synthesis, and Future Research Directions","volume":"31","author":"Kordzadeh","year":"2022","journal-title":"Eur. J. Inf. Syst."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Celma, O., and Cano, P. (2008, January 24\u201327). From hits to niches? or how popular artists can bias music recommendation and discovery. Proceedings of the 2nd KDD, Workshop on Large-Scale Recommender Systems and the Netflix Prize Competition, Las Vegas, NV, USA.","DOI":"10.1145\/1722149.1722154"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Celma, O. (2010). Music Recommendation and Discovery: The Long Tail, Long Fail, and Long Play in the Digital Music Space, Springer Science & Business Media.","DOI":"10.1007\/978-3-642-13287-2"},{"key":"ref_5","first-page":"7309453","article-title":"A session-based song recommendation approach involving user characterization along the play power-law distribution","volume":"2020","author":"Gil","year":"2020","journal-title":"Complexity"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1007\/s10791-017-9312-z","article-title":"Statistical biases in information retrieval metrics for recommender systems","volume":"20","author":"Castells","year":"2017","journal-title":"Inf. Retr. J."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Sun, W., Khenissi, S., Nasraoui, O., and Shafto, P. (2019, January 13\u201317). Debiasing the human-recommender system feedback loop in collaborative filtering. Proceedings of the 2019 World Wide Web Conference (WWW \u201919), San Francisco, CA, USA.","DOI":"10.1145\/3308560.3317303"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Naghiaei, M., Rahmani, H.A., and Dehghan, M. (2022). The Unfairness of Popularity Bias in Book Recommendation. arXiv.","DOI":"10.1007\/978-3-031-09316-6_7"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Wang, X., and Wang, W.H. (2022, January 21\u201324). Providing item-side individual fairness for deep recommender systems. Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency (FAccT \u201922), Seoul, Republic of Korea.","DOI":"10.1145\/3531146.3533079"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Dai, E., and Wang, S. (2021, January 8\u201312). Say no to the discrimination: Learning fair graph neural networks with limited sensitive attribute information. Proceedings of the 14th ACM International Conference on Web Search and Data Mining (WSDM \u201921), Virtual.","DOI":"10.1145\/3437963.3441752"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Dong, Y., Wang, S., Wang, Y., Derr, T., and Li, J. (2022, January 14\u201318). On structural explanation of bias in graph neural networks. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD \u201922), Washington, DC, USA.","DOI":"10.1145\/3534678.3539319"},{"key":"ref_12","unstructured":"Abdollahpouri, H., Mansoury, M., Burke, R., and Mobasher, B. (2019). The unfairness of popularity bias in recommendation. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Abdollahpouri, H., Mansoury, M., Burke, R., Mobasher, B., and Malthouse, E. (2021, January 21\u201325). User centered evaluation of popularity bias in recommender systems. Proceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization (UMAP \u201921), Utrecht, The Netherlands.","DOI":"10.1145\/3450613.3456821"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Dwork, C., Hardt, M., Pitassi, T., Reingold, O., and Zemel, R. (2012, January 8\u201310). Fairness through awareness. Proceedings of the Innovations in Theoretical Computer Science (ITCS \u201912), Cambridge, MA, USA.","DOI":"10.1145\/2090236.2090255"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Islam, R., Keya, K.N., Pan, S., Sarwate, A.D., and Foulds, J.R. (2023). Differential fairness: An intersectional framework for fair AI. Entropy, 25.","DOI":"10.3390\/e25040660"},{"key":"ref_16","unstructured":"Kamishima, T., Akaho, S., Asoh, H., and Sakuma, J. (2012). Enhancement of the neutrality in recommendation. Decisions@RecSys, ACM."},{"key":"ref_17","unstructured":"Kamishima, T., Akaho, S., Asoh, H., and Sakuma, J. (2013). Efficiency improvement of neutrality-enhanced recommendation. Decisions@RecSys, ACM."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Rahman, T., Surma, B., Backes, M., and Zhang, Y. (2019, January 10\u201316). Fairwalk: Towards fair graph embedding. Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI \u201919), Macao, China.","DOI":"10.24963\/ijcai.2019\/456"},{"key":"ref_19","unstructured":"Hardt, M., Price, E., and Srebro, N. (2016, January 5\u201310). Equality of opportunity in supervised learning. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS \u201916), Barcelona, Spain."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1109\/TAI.2021.3133818","article-title":"Fairdrop: Biased edge dropout for enhancing fairness in graph representation learning","volume":"3","author":"Spinelli","year":"2021","journal-title":"IEEE Trans. Artif. Intell."},{"key":"ref_21","unstructured":"Yao, S., and Huang, B. (2017, January 5\u20137). Beyond parity: Fairness objectives for collaborative filtering. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS \u201917), Long Beach, CA, USA."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1007\/s10791-020-09377-x","article-title":"Assessing ranking metrics in top-N recommendation","volume":"23","author":"Valcarce","year":"2020","journal-title":"Inf. Retr. J."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Neophytou, N., Mitra, B., and Stinson, C. (2022, January 10\u201316). Revisiting popularity and demographic biases in recommender evaluation and effectiveness. Proceedings of the European Conference on Information Retrieval (ECIR \u201922), Stavanger, Norway.","DOI":"10.1007\/978-3-030-99736-6_43"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Chizari, N., Tajfar, K., Shoeibi, N., and Moreno-Garc\u00eda, M.N. (2023, January 15\u201317). Quantifying fairness disparities in graph-based neural network recommender systems for protected groups. Proceedings of the 19th International Conference on Web Information Systems and Technologies (WEBIST \u201923), Rome, Italy.","DOI":"10.5220\/0012258700003584"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"102707","DOI":"10.1016\/j.ipm.2021.102707","article-title":"Fair Top-k ranking with multiple protected groups","volume":"59","author":"Zehlike","year":"2022","journal-title":"Inf. Process. Manag."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"102719","DOI":"10.1016\/j.ipm.2021.102719","article-title":"Provider fairness across continents in collaborative recommender systems","volume":"59","author":"Boratto","year":"2022","journal-title":"Inf. Process. Manag."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Aird, A., \u0160tefancov\u00e1, E., All, C., Voida, A., Homola, M., Mattei, N., and Burke, R. (2024, January 14\u201318). Social choice for heterogeneous fairness in recommendation. Proceedings of the 18th ACM Conference on Recommender Systems (RecSys \u201924), Bari, Italy.","DOI":"10.1145\/3640457.3691706"},{"key":"ref_28","unstructured":"Boratto, L., Fabbri, F., Fenu, G., Marras, M., and Medda, G. (2023, January 27\u201330). Explaining unfairness in GNN-based recommendation (Extended Abstract). Proceedings of the Second Learning on Graphs Conference (LoG 2023), Virtual."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Boratto, L., Fabbri, F., Fenu, G., Marras, M., and Medda, G. (2024, January 24\u201328). Robustness in fairness against edge-level perturbations in GNN-based recommendation. Proceedings of the European Conference on Information Retrieval (ECIR \u201924), Glasgow Scotland.","DOI":"10.1007\/978-3-031-56063-7_3"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Chizari, N., Shoeibi, N., and Moreno-Garc\u00eda, M.N. (2022). A comparative analysis of bias amplification in graph neural network approaches for recommender systems. Electronics, 11.","DOI":"10.3390\/electronics11203301"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chizari, N., Tajfar, K., and Moreno-Garc\u00eda, M.N. (2023). Bias assessment approaches for addressing user-centered fairness in GNN-based recommender systems. Information, 14.","DOI":"10.3390\/info14020131"},{"key":"ref_32","unstructured":"Harper, M., and Konstan, J.A. (2025, September 04). The MovieLens Datasets: Distributed by GroupLens at the University of Minnesota. Available online: https:\/\/grouplens.org\/datasets\/movielens\/."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Zhao, W., Zhang, S., Xia, Y., Zhang, Z., Wang, J., Liu, Y., and Tang, J. (2021, January 1\u20135). RecBole: Towards a unified, comprehensive and efficient framework for recommendation algorithms. Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM \u201821), Virtual.","DOI":"10.1145\/3459637.3482016"},{"key":"ref_34","unstructured":"RUCAIBox (2025, September 04). RecBole-GNN: Efficient and extensible GNNs enhanced recommender library based on RecBole. Available online: https:\/\/github.com\/RUCAIBox\/RecBole-GNN."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Pan, C.-H., Qu, Y., Yao, Y., and Wang, M.-J.-S. (2024). HybridGNN: A Self-Supervised Graph Neural Network for Efficient Maximum Matching in Bipartite Graphs. Symmetry, 16.","DOI":"10.20944\/preprints202410.1354.v1"}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/10\/461\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:50:30Z","timestamp":1760035830000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/10\/461"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,8]]},"references-count":35,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["fi17100461"],"URL":"https:\/\/doi.org\/10.3390\/fi17100461","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,8]]}}}