Abstract
Ranking is required for many real applications, such as search, personalisation, recommendation, and filtering. Recent research has focused on developing reliable ranking algorithms that maintain fairness in their outcomes. However, only a few consider multiple protected groups since this extension introduces significant challenges. While useful in the research sector, considering only one binary sensitive feature for handling fairness is inappropriate when the algorithm must be deployed responsibly in real-world applications.
Our work is built on top of Multinomial FA*IR, a Fair Top-k ranking with multiple protected groups, which we extend to provide users the option to balance fairness and utility, adapting the final ranking accordingly. Our experimental results show that alternative better solutions overlooked by Multinomial FA*IR may be found through our approach without violating fairness boundaries. The code of the implemented solution and the experiments are publicly available to the community as a GitHub repository.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In this work we shall use the terms “protected” and “sensitive” group interchangeably to refer to a set of personal attributes, typically”disadvantaged”, that must be considered when dealing with fairness and discrimination issues.
- 2.
E.g. for two protected groups, at position \(j=6\), \(\omega _p=[3,2]\) means that there are three individuals from \(\mathcal {G}^1\), two from \(\mathcal {G}^2\) and the remaining from the non-protected group \(\mathcal {G}^0\).
- 3.
Dataset available at https://archive.ics.uci.edu/ml/datasets/statlog+(german+credit+data).
References
Boratto, L., Marras, M.: Advances in bias-aware recommendation on the web. In: Proceedings of the 14th ACM International Conference on Web Search and Data Mining, pp. 1147–1149 (2021)
Buolamwini, J., Gebru, T.: Gender shades: intersectional accuracy disparities in commercial gender classification. In: FAT, pp. 77–91. PMLR (2018)
Cambria, E., Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N.: A survey on XAI and natural language explanations. Inf. Process. Manag. 60(1), 103111 (2023). https://doi.org/10.1016/j.ipm.2022.103111
Castelnovo, A., Cosentini, A., Malandri, L., Mercorio, F., Mezzanzanica, M.: FFTree: a flexible tree to handle multiple fairness criteria. Inf. Process. Manag. 59(6), 103099 (2022)
Castelnovo, A., et al.: BeFair: addressing fairness in the banking sector. In: 2020 IEEE International Conference on Big Data (Big Data), pp. 3652–3661. IEEE (2020)
Castelnovo, A., Crupi, R., Greco, G., Regoli, D., Penco, I.G., Cosentini, A.C.: A clarification of the nuances in the fairness metrics landscape. Sci. Rep. 12(1), 1–21 (2022)
Castelnovo, A., Crupi, R., Inverardi, N., Regoli, D., Cosentini, A.: Investigating bias with a synthetic data generator: empirical evidence and philosophical interpretation. arXiv preprint arXiv:2209.05889 (2022)
Castelnovo, A., Malandri, L., Mercorio, F., Mezzanzanica, M., Cosentini, A.: Towards fairness through time. In: Machine Learning and Principles and Practice of Knowledge Discovery in Databases. ECML PKDD 2021. Communications in Computer and Information Science, vol. 1524, pp. 647–663. Springer (2021). https://doi.org/10.1007/978-3-030-93736-2_46
Council of Europe, committee of experts on Internet MSI-NET: study on the human rights dimensions of automated data processing techniques and possible regulatory implications (2017)
Crenshaw, K.: Demarginalizing the intersection of race and sex: a black feminist critique of antidiscrimination doctrine, feminist theory and antiracist politics. In: Feminist legal theories, pp. 23–51. Routledge (2013)
Crupi, R., Castelnovo, A., Regoli, D., San Miguel Gonzalez, B.: Counterfactual explanations as interventions in latent space. Data Mining and Knowledge Discovery, pp. 1–37 (2022). https://doi.org/10.1007/s10618-022-00889-2
European Commission: communication on fostering a European approach to AI. https://ec.europa.eu/newsroom/dae/redirection/document/75790 (2021)
Gupta, A., et al.: Online post-processing in rankings for fair utility maximization. In: Proceedings of the 14th ACM International Conference on Web Search and Data Mining, pp. 454–462 (2021)
Hardt, M., Price, E., Srebro, N.: Equality of opportunity in supervised learning. In: Advances in Neural Information Processing Systems 29 (2016)
Kearns, M., Neel, S., Roth, A., Wu, Z.S.: Preventing fairness gerrymandering: auditing and learning for subgroup fairness. In: ICML, pp. 2564–2572. PMLR (2018)
Kendall, M.G.: A new measure of rank correlation. Biometrika 30(1/2), 81–93 (1938)
Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N.: ConvXAI: a system for multimodal interaction with any black-box explainer. Cogn. Comput. 15, 1–32 (2022). https://doi.org/10.1007/s12559-022-10067-7
Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N., Seveso, A.: ContrXT: generating contrastive explanations from any text classifier. Inf. Fusion 81, 103–115 (2022). https://doi.org/10.1016/j.inffus.2021.11.016
Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N., Seveso, A.: The good, the bad, and the explainer: a tool for contrastive explanations of text classifiers. In: Raedt, L.D. (ed.) Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23–29 July 2022, pp. 5936–5939. ijcai.org (2022). https://doi.org/10.24963/ijcai.2022/858
Ramos, G., Boratto, L.: Reputation (in) dependence in ranking systems: demographics influence over output disparities. In: Proceedings of the 43rd international ACM SIGIR conference on Research and Development in Information Retrieval, pp. 2061–2064 (2020)
Ramos, G., Boratto, L., Marras, M.: Robust reputation independence in ranking systems for multiple sensitive attributes. Mach. Learn. 111(10), 3769–3796 (2022)
Robertson, S.E.: The probability ranking principle in IR. J. Document. 33, 294–304 (1977)
Singh, A., Joachims, T.: Fairness of exposure in rankings. In: Proceedings of the 24th ACM SIGKDD ICKDDM, pp. 2219–2228 (2018)
Taesiri, M.R., Nguyen, G., Nguyen, A.: Visual correspondence-based explanations improve AI robustness and human-AI team accuracy. In: Advances in Neural Information Processing Systems (2022)
The European Commission: proposal for a Regulation of the European Parliament laying down harmonised rules on AI (AI Act) (2021). https://digital-strategy.ec.europa.eu/en/library/proposal-regulation-laying-down-harmonised-rules-artificial-intelligence
Yang, K., Stoyanovich, J.: Measuring fairness in ranked outputs. In: Proceedings of the 29th International Conference on Scientific and Statistical Database Management (2017)
Zehlike, M., Bonchi, F., Castillo, C., Hajian, S., Megahed, M., Baeza-Yates, R.: Fa* ir: a fair top-k ranking algorithm. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management (2017)
Zehlike, M., Sühr, T., Baeza-Yates, R., Bonchi, F., Castillo, C., Hajian, S.: Fair top-k ranking with multiple protected groups. IPM 59(1), 102707 (2022)
Zehlike, M., Yang, K., Stoyanovich, J.: Fairness in ranking, part ii: learning-to-rank and recommender systems. ACM Comput. Surv. (CSUR) 55, 3533380 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Alimonda, N., Castelnovo, A., Crupi, R., Mercorio, F., Mezzanzanica, M. (2023). Preserving Utility in Fair Top-k Ranking with Intersectional Bias. In: Boratto, L., Faralli, S., Marras, M., Stilo, G. (eds) Advances in Bias and Fairness in Information Retrieval. BIAS 2023. Communications in Computer and Information Science, vol 1840. Springer, Cham. https://doi.org/10.1007/978-3-031-37249-0_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-37249-0_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-37248-3
Online ISBN: 978-3-031-37249-0
eBook Packages: Computer ScienceComputer Science (R0)