On the apparent conflict between individual and group fairness
Open accessThe DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.
Abstract
A distinction has been drawn in fair machine learning research between 'group' and 'individual' fairness measures. Many technical research papers assume that both are important, but conflicting, and propose ways to minimise the trade-offs between these measures. This paper argues that this apparent conflict is based on a misconception. It draws on discussions from within the fair machine learning research, and from political and legal philosophy, to argue that individual and group fairness are not fundamentally in conflict. First, it outlines accounts of egalitarian fairness which encompass plausible motivations for both group and individual fairness, thereby suggesting that there need be no conflict in principle. Second, it considers the concept of individual justice, from legal philosophy and jurisprudence, which seems similar but actually contradicts the notion of individual fairness as proposed in the fair machine learning literature. The conclusion is that the apparent conflict between individual and group fairness is more of an artefact of the blunt application of fairness measures, rather than a matter of conflicting principles. In practice, this conflict may be resolved by a nuanced consideration of the sources of 'unfairness' in a particular deployment context, and the carefully justified application of measures to mitigate it.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Essentially, all normative assumptions are therefore captured in the choice of similarity metric [7].”
From Algorithmic Unfairness through the Lens of EU Non-Discrimination Law: Or Why the Law is not a Decision Tree (2023) · cites this paper as [7]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“In addition, in cases where substantive differences of opinion exist between expertssuch as in the discourse on computational definitions of fairness [6,8,37]-designers of audit standards must navigate these nuances while also balancing to achieve a set of criteria that provides compliance and is operationalizable at scale.”
From A Framework for Assurance Audits of Algorithmic Systems (2024) · cites this paper as [6]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Mapping the Margins: Intersectionality, Identity Politics, and Violence against Women of Color
Crenshaw, K. (1991) · Stanford Law Review · doi:10.2307/1229039 · Cited by 32,792 · cited 1×
“They may miss unfairness against people as a result of their being at the intersection of multiple kinds of discrimination [15], or groups which are not (yet) defined in anti-discrimination law but may need protecting [49].”
BackgroundDwork, C., Hardt, M., Pitassi, T., Reingold, O., & Zemel, R. (2012) · Proceedings of the 3rd Innovations in Theoretical Computer Science Conference · doi:10.1145/2090236.2090255 · Cited by 3,501 · cited 10×
“…that follows is primarily theoretical, its implications are significant both for researchers and practitioners: • For Fair-ML researchers, the apparent conflict between individual and group measures continues to motivate new research papers many years after it was initially formulated (in [18]).”
BackgroundMethodInfluentialWhat Is the Point of Equality?
Anderson, E. S. (1999) · Ethics · doi:10.1086/233897 · Cited by 3,095 · cited 2×
“Egalitarianism is the notion that people need to be treated in some senses equally, or that certain things need to be distributed according to some egalitarian principle [2, 13, 20, 42, 45, 51].”
BackgroundOn the Currency of Egalitarian Justice
Cohen, G. A. (1989) · Ethics · doi:10.1086/293126 · Cited by 2,917 · cited 1×
“things need to be distributed according to some egalitarian principle [2, 13, 20, 42, 45, 51].”
BackgroundFair prediction with disparate impact: a study of bias in recidivism prediction instruments
Chouldechova, A. (2017) · Big Data · doi:10.1089/big.2016.0047 · Cited by 2,159 · cited 2×
“…recidivism risk scoring algorithm, it was illustrated that it is impossible to simultaneously achieve two group-fairness measures; namely, false positive equality (which reflects the assumption of structural bias) and equal calibration (which reflects the assumption that disparities are benign) [11].”
BackgroundEquality and equal opportunity for welfare
Arneson, R. J. (1989) · Philosophical Studies · doi:10.1007/bf00646210 · Cited by 1,970 · cited 1×
“A prominent approach, known as luck egalitarianism, holds that inequalities between people are only just provided they are not the result of brute luck [4, 29, 46].”
BackgroundFriedman, B., & Nissenbaum, H. (1996) · ACM Transactions on Information Systems · doi:10.1145/230538.230561 · Cited by 1,203 · cited 1×
“Research on bias, fairness and discrimination in socio-technical systems has a long history which significantly predates specific work on fairness in machine learning (see e.g. [23, 24]).”
BackgroundWhat is Equality? Part 1: Equality of Welfare
Dworkin, R. (2018) · The Notion of Equality · doi:10.4324/9781315199795-6 · Cited by 1,180 · cited 1×
“things need to be distributed according to some egalitarian principle [2, 13, 20, 42, 45, 51].”
Background(2013) · Cited by 1,126
Bovens, M., & Zouridis, S. (2002) · Public Administration Review · doi:10.1111/0033-3352.00168 · Cited by 964 · cited 1×
“king are being automated or augmented with algorithms, the need for occasional individualised consideration is one of the reasons for keeping a human-in-the-loop, or ‘screen-level bureaucrat’ on hand [1, 8, 12, 48]. By scrutinising additional information about the individual that the algorithm does not consider, and c…”
Background
Research works printed but not linked: 9
- 10.2139/ssrn.3452030 · doi:10.2139/ssrn.3452030
- Danielle Keats Citron. 2007. Technological due process. Wash. UL Rev. 85 (2007), 1249.
- Oscar Gandy. 1995. It's discrimination, stupid. Resisting the virtual life: The culture and politics of information (1995), 35--47.
- bell hooks. 2014. Ain't IA Woman: Black women and feminism. Routledge New York, NY.
- RenÄl'e Jorgensen Bolinger. 2019. What is the Right to Individualized Judgement? Working Paper (on file with author) (2019).
- Sarah Moss. 2018. Probabilistic knowledge. Oxford University Press.
- John Rawls. 2009. A theory of justice. Harvard university press.
- Amartya Sen. 1992. Inequality reexamined. Clarendon Press.
- Larry S Temkin. 1986. Inequality. Philosophy & Public Affairs (1986), 99--121.
Cited by
Items 101–200 of 377
End-To-End Bias Mitigation: Removing Gender Bias in Deep Learning
Feldman, T., & Peake, A. (2021) · arXiv · doi:10.48550/arxiv.2104.02532 · Cited by 19
“From a social science perspective, this idea is closest to the notion of fairness as consistency [22].”
What Is Fair? Defining Fairness in Machine Learning for Health
Gao, J., Chou, B., McCaw, Z. R., Thurston, H., Varghese, P., Hong, C., & Gronsbell, J. L. (2025) · Statistics in Medicine · doi:10.1002/sim.70234 · Cited by 30
Fair Graph Representation Learning via Diverse Mixture-of-Experts
Liu, Z., Zhang, C., Tian, Y., Zhang, E., Huang, C., Ye, Y., & Zhang, C. (2023) · International World Wide Web Conference (WWW) · doi:10.1145/3543507.3583207 · Cited by 43
“Numerous works have been proposed to address the fairness problem on GNNs, where the concentrations can be mainly divided into two categories: individual fairness [13] and group fairness [3].”
BackgroundMaking Fair ML Software using Trustworthy Explanation
Chakraborty, J., Peng, K., & Menzies, T. (2020) · Figshare · doi:10.6084/m9.figshare.12612449 · Cited by 19
Nápoles, G., & Koumeri, L. K. (2022) · Pattern Recognition Letters · doi:10.1016/j.patrec.2022.01.005 · Cited by 22
“The literature on this subject relies on two dominating notions of fairness: group-based and individual-based fairness measures [10].”
BackgroundA Framework for Assurance Audits of Algorithmic Systems
Lange, B., Lam, K., Blili-Hamelin, B., Davidovic, J., Brown, S., & Hasan, A. (2024) · PhilPapers (PhilPapers Foundation) · Cited by 17
A Multi-Objective Framework for Balancing Fairness and Accuracy in Debiasing Machine Learning Models
Nagpal, R., Khan, A., Borkar, M., & Gupta, A. D. (2024) · Machine Learning and Knowledge Extraction · doi:10.3390/make6030105 · Cited by 21
“Therefore, there is a need to capture individual fairness, which indirectly improves group fairness by reducing information on protected attributes [25].”
BackgroundCastelnovo, A., Malandri, L., Mercorio, F., Mezzanzanica, M., & Cosentini, A. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-93736-2_46 · Cited by 29
The Long Arc of Fairness: Formalisations and Ethical Discourse
Schwöbel, P., & Remmers, P. (2022) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3531146.3534635 · Cited by 25
“University of Chicago Press. https://doi.org/10.7208/chicago/9780226041049.001.0001 [5] Reuben Binns.”
BackgroundInfluentialWiśniewski, J., & Biecek, P. (2022) · The R Journal · doi:10.32614/rj-2022-019 · Cited by 23
Public perception of accuracy-fairness trade-offs in algorithmic decisions in the United States
Mourali, M., Novakowski, D., Pogacar, R., & Brigden, N. (2025) · PLoS ONE · doi:10.1371/journal.pone.0319861 · Cited by 16
“Proposed alternatives aim to reduce disparate impact and promote greater parity of outcomes [17–19].”
iFlipper: Label Flipping for Individual Fairness
Zhang, H., Tae, K. H., Park, J., Chu, X., & Whang, S. E. (2023) · Proceedings of the ACM on Management of Data · doi:10.1145/3588688 · Cited by 22
“All these measures complement each other, and there is a known conflict between group fairness and individual fairness [6, 17] that they cannot be satisfied at the same time because of their different assumptions.”
BackgroundAlgorithmic legitimacy in clinical decision-making
Holm, S. (2023) · Ethics and Information Technology · doi:10.1007/s10676-023-09709-7 · Cited by 18
Fairness through Aleatoric Uncertainty
Tahir, A., Cheng, L., & Liu, H. (2023) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3583780.3614875 · Cited by 35
“The results complement the findings by Binns [6], who suggest that group and individual fairness may not always be conflicting objectives.”
ResultSharma, S., & Shrestha, S. (2024) · Journal of Future Artificial Intelligence and Technologies · doi:10.62411/faith.3048-3719-47 · Cited by 24
“Researchers began to focus on the safety and reliability of AI systems[43].”
Respect as a Lens for the Design of AI Systems
Seymour, W., Kleek, M. G. V., Binns, R., & Murray-Rust, D. (2022) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3514094.3534186 · Cited by 22
“generalisations from other people in the training data [12].”
BackgroundSelf-citationWeerts, H., Royakkers, L. M. M., & Pechenizkiy, M. (2025) · ACM Journal on Responsible Computing · doi:10.1145/3771734 · Cited by 17
“Finally, in Disease detection, some demographic groups may be at higher risk for developing the disease due to confounding factors such as poorer nutrition.”
Forks over knives: Predictive inconsistency in criminal justice algorithmic risk assessment tools
Greene, T., Shmueli, G., Fell, J., Lin, C.-F., & Liu, H.-W. (2022) · Journal of the Royal Statistical Society Series A: Statistics in Society · doi:10.1111/rssa.12966 · Cited by 15
“The discussion of competing fairness metrics also highlights a deeper issue: the distinction between individual and group justice (Binns, 2020; Mitchell et al., 2021).”
BackgroundIonescu, S., Hannák, A., & Pagan, N. (2023) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3604915.3608841 · Cited by 22
“, inequalities between protected and unprotected groups [5, 15]).”
BackgroundPurdy, J., & Glass, B. (2022) · Children and Youth Services Review · doi:10.1016/j.childyouth.2022.106777 · Cited by 16
Weith, H., & Matt, C. (2023) · Electronic Markets · doi:10.1007/s12525-023-00668-x · Cited by 17
“According to Binns (2019), explanations comparing a result to previous similar results had the highest impact on fairness perceptions.”
ResultReranking Individuals: The Effect of Fair Classification Within-Groups
Goethals, S., Favier, M., & Calders, T. (2026) · ACM Journal on Responsible Computing · doi:10.1145/3802540 · Cited by 15
“Another popular approach to assess fairness in machine learning models is individual fairness , which demands that similar individuals receive similar outcomes in a decision-making process, regardless of their group membership [4, 14].”
Neutralizing Self-Selection Bias in Sampling for SortitionPreprint
Flanigan, B., Gölz, P., Gupta, A., & Procaccia, A. D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.10498 · Cited by 14
“Achieving simultaneous group-and individual-level fairness is a commonly discussed goal in fair machine learning [5, 12, 15], but one that has proven somewhat elusive.”
Equalised Odds is not Equal Individual Odds: Post-processing for Group and Individual Fairness
Small, E. A., Sokol, K., Manning, D., Salim, F. D., & Chan, J. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3658989 · Cited by 21
Optimizing fairness and accuracy: a Pareto optimal approach for decision-making
Nagpal, R., Shahsavarifar, R., Goyal, V., & Gupta, A. D. (2024) · AI and Ethics · doi:10.1007/s43681-024-00508-4 · Cited by 17
“While group and individual fairness are often framed as competing definitions, Binns [14] discusses how approaches that aim to capture individual fairness could indirectly improve group fairness by reducing the reliance on protected attributes, contesting the notion of competing objectives for…”
Ethics at the heart of AI regulation
Fessenko, D. S., & Jasperse, A. (2024) · AI and Ethics · doi:10.1007/s43681-024-00562-y · Cited by 19
“Adequate fairness measures also involve the choice of an appropriate notion of justice that AI developers would build into their AI models, technical approaches, and statistical measures for accuracy [9, 85–87].”
Revisiting Technical Bias Mitigation Strategies
Mahamadou, A. J. D., & Trotsyuk, A. A. (2025) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-103123-095737 · Cited by 14
Enforcing fairness using ensemble of diverse Pareto-optimal models
Guardieiro, V., Raimundo, M. M., & Poco, J. (2023) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-023-00922-y · Cited by 18
“It is noteworthy that equal opportunity might also conflict with accuracy, but it can be alleviated under ideal conditions (Dutta et al. 2020), and group fairness and ideal fairness can also be conflicting (Speicher et al. 2018) due to a poor conceptualization of the problem (Binns 2020).”
BackgroundInfluentialTowards Machine Learning Fairness Education in a Natural Language Processing Course
Dobesh, S. J., Miller, T., Newman, P., Liu, Y., & Elglaly, Y. N. (2023) · ACM Technical Symposium on Computer Science Education (SIGCSE) · doi:10.1145/3545945.3569802 · Cited by 17
“This fairness includes egalitarian considerations for protected demographics by attempting to identify and mitigate biases that disproportionately affect them [8].”
BackgroundSoftware doping analysis for human oversight
Biewer, S., Baum, K. L., Sterz, S., Hermanns, H., Hetmank, S., Langer, M., Lauber-Rönsberg, A., & Lehr, F. (2024) · Formal Methods in System Design · doi:10.1007/s10703-024-00445-2 · Cited by 13
When Mitigating Bias is Unfair: Multiplicity and Arbitrariness in Algorithmic Group Fairness
Krčo, N., Laugel, T., Grari, V., Loubes, J., & Detyniecki, M. (2025) · IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · doi:10.1109/satml64287.2025.00046 · Cited by 14
“By turning a social problem into a mathematical optimization one, works in algorithmic fairness have thus been shown to fail to account for several key aspects of the bias problem, generally suffering from being too simplistic [7], [8] and ignoring any social context [9], [10].”
Representativity Fairness in Clustering
Deepak, P., & Abraham, S. S. (2020) · ACM Web Science Conference (WebSci) · doi:10.1145/3394231.3397910 · Cited by 16
“Though individual and group fairness have been traditionally treated as distinct and conflicting within work on fair machine learning, this dichotomy has been subject to some recent criticism (refer [5]).”
BackgroundFormalising Anti-Discrimination Law in Automated Decision Systems
Sargeant, H., & Magnusson, M. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732015 · Cited by 17
“Individual approaches to parity have also considered whether otherwise identical individuals are treated differently if they have different protected attributes [18, 34, 76].”
Counterfactual Fairness Evaluation of Machine Learning Models on Educational Datasets
Kim, W., & Kim, H. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-98284-2_7 · Cited by 16
Han, S., Lee, S., Wu, F., Kim, S., Wu, C., Wang, X., Xie, X., & Cha, M. (2023) · International World Wide Web Conference (WWW) · doi:10.1145/3543507.3583480 · Cited by 20
“They also consider only group-level fairness, missing out on individual-level fairness [6].”
BackgroundWhat will it take to generate fairness-preserving explanations?Preprint
Dai, J. C., Upadhyay, S., Bach, S. H., & Lakkaraju, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.13346 · Cited by 15
“Though there is debate about the extent to which counterfactual or individual fairness is distinct (if not orthogonal) from group fairness (Lahoti et al., 2019; Binns, 2020), a “fairness-preserving” explanation should nevertheless capture the counterfactual behavior of the black-box model.”
BackgroundGroup Fairness via Group Consensus
Chan, E., Liu, Z., Qiu, R., Zhang, Y., Maciejewski, R., & Tong, H. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3659006 · Cited by 27
“Being a broad concept, fairness has been defined in a wide variety of ways, the most popular views being (1) individual fairness [5, 14, 16, 29, 32, 36], in which similar individuals receive similar outcomes, and (2) group fairness, which aims to achieve some statistical parity among groups [11].”
BackgroundWhat’s Impossible about Algorithmic Fairness?
Sahlgren, O. (2024) · Philosophy & Technology · doi:10.1007/s13347-024-00814-z · Cited by 16
“But the two fairness notions will in those cases conflict because they are practically incompatible in the actual setting where the decision-maker would wish to produce fair predictions (see also Green, 2020, Green, 2022, Fazelpour & Lipton, 2020, cf. Binns, 2020).”
Plevris, V. (2025) · Journal of Civil Engineering Education · doi:10.1061/jceecd.eieng-2193 · Cited by 11
Luo, L. K., Nakao, Y., Chollet, M., Inakoshi, H., & Stumpf, S. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3710908 · Cited by 13
“Despite being theoretically attractive, individual fairness also poses challenges in practical application, notably in calculating similarity, which involves defining similarity and determining the scope of individuals to be considered in these comparisons [7, 8, 65].”
InfluentialBull, C. F., Kisely, S. R., Betts, K. S., & Hu, Y. (2025) · Child Abuse & Neglect · doi:10.1016/j.chiabu.2025.107630 · Cited by 14
Machine Learning and the Meaning of Equal Treatment
Simons, J., Bhatti, S. A., & Weller, A. (2021) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3461702.3462556 · Cited by 18
“Scholars have articulated illuminating descriptions of impossibility results [23, 59] and the principles that underpin group- and individual-level fairness definitions [21].”
BackgroundModelling the long-term fairness dynamics of data-driven targeted help on job seekers
Scher, S., Kopeinik, S., Trügler, A., & Kowald, D. (2023) · Scientific Reports · doi:10.1038/s41598-023-28874-9 · Cited by 17
Ruggieri, S., Álvarez, J. M., Pugnana, A., State, L., & Turini, F. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i13.26798 · Cited by 44
“See the previous surveys and (R¨az 2021; Wachter, Mittelstadt, and Rus-sell 2021; Hertweck, Heitz, and Loi 2021; Binns 2020) for a discussion of the moral/legal bases and relative merits of the various fairness notions and metrics.”
BackgroundWhen Small Decisions Have Big Impact: Fairness Implications of Algorithmic Profiling Schemes
Kern, C. A., Bach, R. L., Mautner, H., & Kreuter, F. (2024) · ACM Journal on Responsible Computing · doi:10.1145/3689485 · Cited by 14
fairmodels: A Flexible Tool For Bias Detection, Visualization, And MitigationPreprint
Wiśniewski, J., & Biecek, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.00507 · Cited by 13
“If we factor in certain assumptions such as whether the disparities are due to personal choices or unjust structures (Binns, 2020).”
The Use of AI in HRM and Management Processes: The Promise of Diversity, Equity, and Inclusion
April, K. A., & Daya, P. (2025) · International perspectives on equality, diversity and inclusion · doi:10.1108/s2051-233320250000012012 · Cited by 14
Managing Transparency Fairness Accountability in AI for Sustainable Human Resource Management
Setiawati, R., Kusmara, A., & Kuusk, T. (2025) · International Conference on Creative Communication and Innovative Technology (ICCIT) · doi:10.1109/iccit65724.2025.11166968 · Cited by 19
Artificial Intelligence in Recruitment: A Multivocal Review of Benefits, Challenges, and Strategies
Trovão, H., Mamede, H. S., Trigo, P., & Santos, V. (2025) · Emerging Science Journal · doi:10.28991/esj-2025-09-06-030 · Cited by 10
“These works show how AI tools can automate processes such as résumé parsing and initial interviews while pinpointing concerns about fairness and accountability [10, 11].”
Discrimination-Aware Process Mining: A Discussion
Pohl, T., Qafari, M. S., & van der Aalst, W. M. P. (2023) · Lecture notes in business information processing · doi:10.1007/978-3-031-27815-0_8 · Cited by 13
Group fairness without demographics using social networks
Liu, D., Do, V., Usunier, N., & Nickel, M. (2023) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3593013.3594091 · Cited by 17
“, fairness gerrymandering) or for groups that are not included in, for instance, anti-discrimination laws but may need protecting [21, 113].”
BackgroundPurificato, E., Boratto, L., & Luca, E. W. D. (2024) · Minds and Machines · doi:10.1007/s11023-024-09685-x · Cited by 12
“In particular, in this paper, we refer to group fairness , which is primarily focused on the outcomes of privileged and unprivileged groups (Binns, 2020).”
Fair classification via Monte Carlo policy gradient method
Petrović, A., Nikolić, M., Jovanović, M., Bijanić, M., & Delibašić, B. (2021) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2021.104398 · Cited by 14
Explaining classification performance and bias via network structure and sampling technique
Espín-Noboa, L., Karimi, F., Ribeiro, B., Lerman, K., & Wagner, C. (2021) · Applied Network Science · doi:10.1007/s41109-021-00394-3 · Cited by 11
“…has been an increase of research focusing on mitigating bias (Raghavan et al. 2020; Dixon et al. 2018; Krasanakiset al. 2018) and guaranteeing individual and group fairness while preserving accuracy in classification algorithms (Dwork et al. 2018; Binns 2020; Kallus et al. 2019; Zafar et al. 2017).”
BackgroundOvercoming Fairness Trade-offs via Pre-processing: A Causal PerspectivePreprint
Leininger, C., Rittel, S., & Bothmann, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.14710 · Cited by 10
“A similar observation is made by Binns [6], who argue that the conflict between individual and group fairness depends on the worldview and the underlying normative principles a decision-maker considers.”
BiasTrap: Runtime Detection of Biased Prediction in Machine Learning Systems
Mamman, H., Basri, S. B., Balogun, A. O., Imam, A. A., Kumar, G., & Capretz, L. F. (2024) · Journal of Advanced Research in Applied Sciences and Engineering Technology · doi:10.37934/araset.40.2.127139 · Cited by 9
Poe, R. L., & Mestari, S. Z. E. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3659015 · Cited by 14
“The maxim of similar treatment that individual fairness embodies is an Aristotelian principle of consistency [13].”
BackgroundRAWLSNET: Altering Bayesian Networks to Encode Rawlsian Fair Equality of Opportunity
Liu, D., Shafi, Z., Fleisher, W., Eliassi‐Rad, T., & Alfeld, S. (2021) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3461702.3462618 · Cited by 11
“For instance, Binns argues that FEO considerations justify appeals to group fairness metrics in certain contexts and individual fairness metrics in other contexts (Binns 2020).”
BackgroundInsights From Insurance for Fair Machine Learning
Fröhlich, C., & Williamson, R. C. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3658914 · Cited by 14
“19 For the same reason, what is called individual fairness in machine learning fails to be genuinely individual, as pointed out by Binns ( ).”
BackgroundFroehlich, L., & Weydner-Volkmann, S. (2024) · Journal of Learning Analytics · doi:10.18608/jla.2023.8301 · Cited by 9
“(Binns, 2020, p. 516) It is sometimes argued that notions of individual and group fairness are in conflict and that using group fairness measures to influence the measurement and model learning phases may violate conditions of individual fairness.”
InfluentialSmuha, N. A. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.4093683 · Cited by 9
Bennett, R., Hemmati, M., Ramesh, R., & Razzaghi, T. (2024) · Springer optimization and its applications · doi:10.1007/978-3-031-74006-0_2 · Cited by 13
Making ML Models Fairer Through Explanations: The Case of LimeOut
Alves, G., Bhargava, V., Couceiro, M., & Napoli, A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-72610-2_1 · Cited by 11
FairRoad: Achieving Fairness for Recommender Systems with Optimized Antidote Data
Fang, M., Liu, J., Momma, M., & Sun, Y. (2022) · ACM Symposium on Access Control Models and Technologies (SACMAT) · doi:10.1145/3532105.3535023 · Cited by 12
“In recent years, algorithmic fairness research has received increasing attention in the learning community [7– 10, 15, 23–27, 31, 33–35, 39–42, 45, 46, 48–50, 53, 55, 59, 65, 66, 68, 72, 73, 76–78].”
Yokota, T., & Nakao, Y. (2022) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3511047.3538033 · Cited by 8
“Research shows there are conflicting fairness criteria such as ‘individual’ and ‘group’ fairness [3, 12].”
BackgroundFairness Certification for Natural Language Processing and Large Language Models
Freiberger, V., & Buchmann, E. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-66329-1_39 · Cited by 13
Forks Over Knives: Predictive Inconsistency in Criminal Justice Algorithmic Risk Assessment Tools
Greene, T., Shmueli, G., Fell, J., Lin, C.-F., & Liu, H.-W. (2020) · arXiv · doi:10.48550/arxiv.2012.00289 · Cited by 8
Yang, M. M.-H. (2026) · Human Resource Management Journal · doi:10.1111/1748-8583.70044 · Cited by 9
Shukla, N. (2025) · Frontiers in Communication · doi:10.3389/fcomm.2025.1380252 · Cited by 8
BiaScope: Visual Unfairness Diagnosis for Graph Embeddings
Rissaki, A., Scarone, B., Liu, D., Pandey, A., Klein, B., Eliassi‐Rad, T., & Borkin, M. A. (2022) · IEEE Visualization in Data Science (VDS) · doi:10.1109/vds57266.2022.00008 · Cited by 11
“In particular, these notions can model discrimination either against groups [49] or individuals [35] and it is well-established that trade-offs exist between the two types [11,37].”
BackgroundOn the trade-off between ranking effectiveness and fairness
Melucci, M. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122709 · Cited by 9
Algorithm Bias and Perceived Fairness: A Comprehensive Scoping Review
Saryazdi, A. H. (2024) · ACM SIGCPR Conference on Computer Personnel Research (SIGCPR) · doi:10.1145/3632634.3655848 · Cited by 7
“When there is an insufficient number of qualified candidates in one group, the model might end up granting interviews to unqualified candidates from that group, which comes at the cost of ignoring qualified candidates from the other group [24].”
BackgroundTowards Responsible AI in Education: Hybrid Recommendation System for K-12 Students Case Study
Drushchak, N., Tyshchenko, V., & Polyakovska, N. (2025) · doi:10.1109/raie66699.2025.00015 · Cited by 11
“Binns [5] and Burke [8] proposed fairness-aware frameworks to address these issues.”
Sarkar, P., & Liem, C. C. S. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3637360 · Cited by 7
Black-Box Testing and Auditing of Bias in ADM Systems
Krafft, T. D., Hauer, M. P., & Zweig, K. A. (2024) · Minds and Machines · doi:10.1007/s11023-024-09666-0 · Cited by 10
“• The type of evaluation (qualitative, quantitative): When a system under test is to be evaluated in terms of bias, there is a difference between an evaluation of its general, statistical behaviour and its behaviour in individual cases (Binns, 2020).”
AIM: Attributing, Interpreting, Mitigating Data Unfairness
Liu, Z., Qiu, R., Zeng, Z., Zhu, Y., Hamann, H. F., & Tong, H. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3671797 · Cited by 17
“With its root in social, ethical and legal literature on fairness [8, 17, 20, 54], we posit that a good sample bias criterion should be able to robustly capture various prejudices encoded in the .”
A General Concave Fairness Framework for Influence Maximization Based on Poverty Reward
Wang, Z., Zhao, J., Sun, C., Rui, X., & Yu, P. S. (2024) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3701737 · Cited by 6
“The motivation for individual fairness is initially the concern that simple statistical parity between protected groups in each outcome class could be intuitively unfair at the individual level [4].”
Performance Evaluation for Detecting and Alleviating Biases in Predictive Machine Learning Models
Khakurel, U. B., Abdelmoumin, G., & Rawat, D. B. (2025) · ACM transactions on probabilistic machine learning. · doi:10.1145/3729432 · Cited by 6
AI and Diversity: Ensuring Fairness in Automated Decision-Making
Subrahmanyam, S., & Baz, B. E. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-3104-1.ch002 · Cited by 6
Fairness analysis of machine learning predictions of aggression in acute psychiatric care
Wang, Y., Sikstrom, L., Xiao, R., Findlay, Z., Zaheer, J., Hill, S., & Maslej, M. M. (2026) · npj Mental Health Research · doi:10.1038/s44184-026-00194-6 · Cited by 6
“Individual fairness often reliesoncounterfactualorexplanation-basedwaystode fi nefairness,neither of which were assessed in this study 60 .”
Informational richness and its impact on algorithmic fairness
Bello, M. D., & Gong, R. (2023) · Philosophical Studies · doi:10.1007/s11098-023-02004-7 · Cited by 7
“Our claim that the impossibility theorems constitute an inner critique underscores the fact that violations of fairness criteria can occur absent exogenous sources of bias in the data or in society.”
Fair Algorithm Design: Fair and Efficacious Machine Scheduling
Niu, A., Totschnig, A., & Vetta, A. R. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43254-5_14 · Cited by 8
The Automated Future: How AI and Automation Are Revolutionizing Online Services
Desmal, A. J., Alsaeed, M., Hamid, S. B., & Zolait, A. H. (2023) · IEEE International Conference on Engineering Technologies and Applied Sciences (ICETAS) · doi:10.1109/icetas59148.2023.10346472 · Cited by 9
“Algorithms also frequently perpetuate and amplify socioeconomic biases, leading to issues like discrimination in advertising delivery, search results, or recommendations [23].”
BackgroundTaming the AI Monster: Monitoring of Individual Fairness for Effective Human Oversight
Baum, K. L., Biewer, S., Hermanns, H., Hetmank, S., Langer, M., Lauber-Rönsberg, A., & Sterz, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-66149-5_1 · Cited by 6
Fair Personalized Learner Modeling Without Sensitive Attributes
Xu, H., Hou, M., Wu, L., Liu, F., Yang, Y., Bai, H., Hong, R., & Wang, M. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714787 · Cited by 11
“Existing studies on fairness can generally be divided into two categories [38]: individual fairness [20, 39] and group fairness [18, 40, 41].”
Ethical Considerations in Data-Driven Fake News Detection
Deepak, P. (2020) · The information retrieval series · doi:10.1007/978-3-030-62696-9_10 · Cited by 10
Robustness of Fairness: An Experimental Analysis
Kamp, S., Zhao, A. L. L., & Kutty, S. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-93736-2_43 · Cited by 7
“There is no single agreed-upon measure of fairness since different contexts may require different criteria of measurement, including exogenous concerns like privacy-preservation [5, 6, 42].”
BackgroundMethodLee, M. S. A., Floridi, L., & Singh, J. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3679975 · Cited by 10
Kaas, M. H. L., Burr, C., Porter, Z., Ozturk, B., Ryan, P., Katell, M. A., Polo, N., Westerling, K., & Habli, I. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2406.09029 · Cited by 7
“This brings us to the first of two limitations of most current work on AI fairness, which have already been acknowledged by others in the literature [5,43,48].”
BackgroundCo-Producing AI: Toward an Augmented, Participatory Lifecycle
Mushkani, R., Berard, H., Ammar, T., Chatonnier, C., & Koseki, S. (2025) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1609/aies.v8i2.36674 · Cited by 5
“Numerous fairness criteria, such as statistical parity, equal opportunity, and individual fairness, coexist and sometimes conflict (Bellamy et al. 2019; Chouldechova 2017; Dwork et al. 2012; Hardt, Price, and Srebro 2016; Binns 2020; Hoffmann et al. 2022; Lepri et al. 2018).”
The role of luck in the success of social media influencers
Ionescu, S., Hannák, A., & Pagan, N. (2023) · Applied Network Science · doi:10.1007/s41109-023-00573-4 · Cited by 8
“…the various fairness metrics, our focus is on individual fairness , which evaluates the extent to which similarly qualified individuals receive similar quality outcomes (see (Binns 2020) for a comprehensive overview of its significance and its apparent incompatibility with other fairness metrics).”
BackgroundGerrymandering individual fairness
Räz, T. (2023) · Artificial Intelligence · doi:10.1016/j.artint.2023.104035 · Cited by 7
Equitable Top-k Results for Long Tail Data
Islam, M. M., Asadi, M., & Roy, S. B. (2023) · Proceedings of the ACM on Management of Data · doi:10.1145/3626727 · Cited by 7
Bias in Text Generative Open AI
Devisetti, S. A. (2024) · Indian Journal of Artificial Intelligence and Neural Networking · doi:10.54105/ijainn.b1084.04020224 · Cited by 5
Strotherm, J., Müller, A., Hammer, B., & Paaßen, B. (2024) · Springer eBooks · doi:10.1007/978-3-658-43816-6_9 · Cited by 7
LLANES, N. P., Talamor, M. A., Jaspe, S. M., & Pedroso, J. E. (2025) · JOURNAL OF DIGITAL LEARNING AND DISTANCE EDUCATION · doi:10.56778/jdlde.v4i4.557 · Cited by 5
“Artificial Intelligence may seem fair by its personalized support to individuals, but it is still technically unfair to those who have more and easier access to technology (Binns, 2020).”
FETA: Fairness Enforced Verifying, Training, and Predicting Algorithms for Neural Networks
Mohammadi, K., Sivaraman, A., & Farnadi, G. (2023) · ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO) · doi:10.1145/3617694.3623243 · Cited by 5
“However, as previously demonstrated [8], it is not straightforward to achieve both group fairness and individual fairness in a single model.”
BackgroundCausal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spaces
Ehyaei, A.-R., Mohammadi, K., Karimi, A.-H., Samadi, S., & Farnadi, G. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i10.29070 · Cited by 9
Fairness-Aware Influence Blocking Maximization in Social Networks
Xiao, Y., Liu, D., Yang, L., & Li, Z. (2025) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2025.3568423 · Cited by 4
“…for the entire network is defined as and for a specific community C i , the community-level saving ratio is defined as Maximin fairness, a widely used fairness measure [42], enhances the protection effectiveness of the least well-off group by maximizing the minimum saving ratio among all communities.”
Safeguarding human dignity: A narrative review of prohibited AI practices under the EU AI Act
Deckker, D., & Sumanasekara, S. (2025) · World Journal of Advanced Research and Reviews · doi:10.30574/wjarr.2025.26.3.2193 · Cited by 4
“Global instruments such as the UNESCO Recommendation on the Ethics of AI (2021) and the OECD AI Principles (2019) further underscore the importance of rights-based approaches.”
Metadata
- Authors
- Binns, R.
- Affiliations
- University of Oxford (GB)
- Corresponding author
- Binns, Reuben
- ORCID
- Binns, Reuben
- Venue
- Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency
- Publisher
- ACM
- Published
- 2020-01-27
- Pages
- 514-524
- OpenAlex
- W2996424229
- Cited by
- 312
- References
- 46
- Citations by year
- 2026: 26 · 2025: 59 · 2024: 61 · 2023: 62 · 2022: 45 · 2021: 41 · 2020: 17
- FWCI
- 42.79
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Conference on Fairness, Accountability, and Transparency (FAccT) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- EPSRC (N02334X/1)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Social Sciences › Political Science and International Relations › Political Philosophy and Ethics
- Social Sciences › Law › Discrimination and Equality Law
- Keywords
- individual fairness, group fairness, algorithmic fairness, individual justice, legal theory, fairness metrics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.