Algorithmic Fairness

PageRank (PR) is a fundamental algorithm in graph machine learning tasks. Owing to the increasing importance of algorithmic fairness, we consider the problem of computing PR vectors subject to various group-fairness criteria based on sensitive attributes of the vertices. At present, principled algorithms for this problem are lacking - some cannot guarantee that a target fairness level is achieved, while others do not feature optimality guarantees. In order to overcome these shortcomings, we put forth a unified in-processing convex optimization framework, termed FairRARI, for tackling different group-fairness criteria in a ``plug and play'' fashion. Leveraging a variational formulation of PR, the framework computes fair PR vectors by solving a strongly convex optimization problem with fairness constraints, thereby ensuring that a target fairness level is achieved. We further introduce three different fairness criteria which can be efficiently tackled using FairRARI to compute fair PR vectors with the same asymptotic time-complexity as the original PR algorithm. Extensive experiments on real-world datasets showcase that FairRARI outperforms existing methods in terms of utility, while achieving the desired fairness levels across multiple vertex groups; thereby highlighting its effectiveness.

We study the Pareto frontier (optimal trade-off) between utility and separation, a fairness criterion requiring predictive independence from sensitive attributes conditional on the true outcome. Through an information-theoretic lens, we prove a characterization of the utility-separation Pareto frontier, establish its concavity, and thereby prove the increasing marginal cost of separation in terms of utility. In addition, we characterize the conditions under which this trade-off becomes strict, providing a guide for trade-off selection in practice. Based on the theoretical characterization, we develop an empirical regularizer based on conditional mutual information (CMI) between predictions and sensitive attributes given the true outcome. The CMI regularizer is compatible with any deep model trained via gradient-based optimization and serves as a scalar monitor of residual separation violations, offering tractable guarantees during training. Finally, numerical experiments support our theoretical findings: across COMPAS, UCI Adult, UCI Bank, and CelebA, the proposed method substantially reduces separation violations while matching or exceeding the utility of established baseline methods. This study thus offers a provable, stable, and flexible approach to enforcing separation in deep learning.

We study a stylized model of infrastructure investment in public transportation. In our model, each agent travels between a pair of terminals in a network captured by a weighted graph, where edge weights represent distances. The central planner can reduce the travel time along a fixed number of edges, with the goal of maximizing the utilitarian or egalitarian welfare. When there is only one agent, we provide a polynomial-time algorithm that combines Dijkstra's algorithm with a dynamic program. We then demonstrate how to use this algorithm as a subroutine to solve the problem for two agents. Generalizing this idea, we present an XP algorithm parameterized by the number of agents $n$; however, our problem turns out to be W[1]-hard with respect to $n$. Nevertheless, we establish a fixed-parameter tractability result for the special case where all agents travel to a common hub. If the number of agents is variable, we obtain NP-completeness and inapproximability results. We discuss implications of our results for a related model of railway network design.

Nash regret has recently emerged as a principled fairness-aware performance metric for stochastic multi-armed bandits, motivated by the Nash Social Welfare objective. Although this notion has been extended to linear bandits, existing results suffer from suboptimality in ambient dimension $d$, stemming from proof techniques that rely on restrictive concentration inequalities. In this work, we resolve this open problem by introducing new analytical tools that yield an order-optimal Nash regret bound in linear bandits. Beyond Nash regret, we initiate the study of $p$-means regret in linear bandits, a unifying framework that interpolates between fairness and utility objectives and strictly generalizes Nash regret. We propose a generic algorithmic framework, FairLinBandit, that works as a meta-algorithm on top of any linear bandit strategy. We instantiate this framework using two bandit algorithms: Phased Elimination and Upper Confidence Bound, and prove that both achieve sublinear $p$-means regret for the entire range of $p$. Extensive experiments on linear bandit instances generated from real-world datasets demonstrate that our methods consistently outperform the existing state-of-the-art baseline.

In multiparty multiobjective optimization problems, solution sets are usually evaluated using classical performance metrics, aggregated across DMs. However, such mean-based evaluations may be unfair by favoring certain parties, as they assume identical geometric approximation quality to each party's PF carries comparable evaluative significance. Moreover, prevailing notions of MPMOP optimal solutions are restricted to strictly common Pareto optimal solutions, representing a narrow form of cooperation in multiparty decision making scenarios. These limitations obscure whether a solution set reflects balanced relative gains or meaningful consensus among heterogeneous DMs. To address these issues, this paper develops a fairness-aware performance evaluation framework grounded in a generalized notion of consensus solutions. From a cooperative game-theoretic perspective, we formalize four axioms that a fairness-aware evaluation function for MPMOPs should satisfy. By introducing a concession rate vector to quantify acceptable compromises by individual DMs, we generalize the classical definition of MPMOP optimal solutions and embed classical performance metrics into a Nash-product-based evaluation framework, which is theoretically shown to satisfy all axioms. To support empirical validation, we further construct benchmark problems that extend existing MPMOP suites by incorporating consensus-deficient negotiation structures. Experimental results demonstrate that the proposed evaluation framework is able to distinguish algorithmic performance in a manner consistent with consensus-aware fairness considerations. Specifically, algorithms converging toward strictly common solutions are assigned higher evaluation scores when such solutions exist, whereas in the absence of strictly common solutions, algorithms that effectively cover the commonly acceptable region are more favorably evaluated.

The deployment of Artificial Intelligence in high-risk domains, such as finance and healthcare, necessitates models that are both fair and transparent. While regulatory frameworks, including the EU's AI Act, mandate bias mitigation, they are deliberately vague about the definition of bias. In line with existing research, we argue that true fairness requires addressing bias at the intersections of protected groups. We propose a unified framework that leverages Mixed-Integer Optimization (MIO) to train intersectionally fair and intrinsically interpretable classifiers. We prove the equivalence of two measures of intersectional fairness (MSD and SPSF) in detecting the most unfair subgroup and empirically demonstrate that our MIO-based algorithm improves performance in finding bias. We train high-performing, interpretable classifiers that bound intersectional bias below an acceptable threshold, offering a robust solution for regulated industries and beyond.

Large Language Models (LLMs) exhibit systematic biases across demographic groups. Auditing is proposed as an accountability tool for black-box LLM applications, but suffers from resource-intensive query access. We conceptualise auditing as uncertainty estimation over a target fairness metric and introduce BAFA, the Bounded Active Fairness Auditor for query-efficient auditing of black-box LLMs. BAFA maintains a version space of surrogate models consistent with queried scores and computes uncertainty intervals for fairness metrics (e.g., $Δ$ AUC) via constrained empirical risk minimisation. Active query selection narrows these intervals to reduce estimation error. We evaluate BAFA on two standard fairness dataset case studies: \textsc{CivilComments} and \textsc{Bias-in-Bios}, comparing against stratified sampling, power sampling, and ablations. BAFA achieves target error thresholds with up to 40$\times$ fewer queries than stratified sampling (e.g., 144 vs 5,956 queries at $\varepsilon=0.02$ for \textsc{CivilComments}) for tight thresholds, demonstrates substantially better performance over time, and shows lower variance across runs. These results suggest that active sampling can reduce resources needed for independent fairness auditing with LLMs, supporting continuous model evaluations.

Accurately predicting mortality risk in intensive care unit (ICU) patients is critical for clinical decision-making. Large language models (LLMs) are increasingly explored for clinical prediction using structured medical data, but their outputs may exhibit demographic disparities. Mitigating such disparities without degrading predictive performance remains challenging. We systematically investigate demographic bias in LLM-based ICU mortality prediction and propose Case-Based Prompting (CAP), a training-free framework designed to improve the empirical balance between predictive performance and subgroup fairness. CAP retrieves clinically similar historical misprediction and demographic-sensitive cases with known outcomes and incorporates them as case-level contextual evidence. We further evaluate model discrimination, subgroup fairness, and feature-dependence consistency. On MIMIC-IV, CAP improved AUROC from 0.806 to 0.873 and AUPRC from 0.497 to 0.694 compared with the Baseline Prompt. CAP also reduced several subgroup disparities, particularly for sex and White-Black comparisons, although age-related disparities remained non-negligible. Controlled demographic-information ablations showed that removing demographic information did not uniformly improve both predictive performance and subgroup fairness, indicating distinct performance-fairness patterns rather than a uniform benefit from demographic suppression. Feature-dependence analysis showed generally consistent expressed clinical factor patterns across demographic subgroups. These findings suggest that CAP is a promising inference-time strategy for LLM-based clinical prediction under the evaluated retrospective setting. Further validation across additional LLMs, external datasets, and prospective clinical scenarios is required before deployment.

As deep learning (DL) techniques become integral to various applications, ensuring model fairness while maintaining high performance has become increasingly critical, particularly in sensitive fields such as medical diagnosis. Although a variety of bias-mitigation methods have been proposed, many rely on computationally expensive debiasing strategies or suffer substantial drops in model accuracy, which limits their practicality in real-world, resource-constrained settings. To address this issue, we propose a fairness-oriented low rank factorization (LRF) framework that leverages singular value decomposition (SVD) to improve DL model fairness. Unlike traditional SVD, which is mainly used for model compression by decomposing and reducing weight matrices, our work shows that SVD can also serve as an effective tool for fairness enhancement. Specifically, we observed that elements in the unitary matrices obtained from SVD contribute unequally to model bias across groups defined by sensitive attributes. Motivated by this observation, we propose a method, named FairLRF, that selectively removes bias-inducing elements from unitary matrices to reduce group disparities, thus enhancing model fairness. Extensive experiments show that our method outperforms conventional LRF methods as well as state-of-the-art fairness-enhancing techniques in terms of improving fairness while maintaining accuracy. Additionally, an ablation study examines how major hyper-parameters may influence the performance of processed models. To the best of our knowledge, this is the first work utilizing SVD not primarily for compression but for fairness enhancement of DL classifications.

We treat the internals of generative models as mechanistic objects rather than black boxes. We introduce \textbf{Attribution Graphs} (AGs), which extend GradCAM++ to circuit-level representations, and \textbf{Causal Probing}, a do-calculus intervention method for identifying causal latent structures, enabling detection and correction of spurious correlations, demographic biases, and misaligned decision circuits during training. We further propose the \textbf{Cognitive Alignment Score (CAS)}, quantifying agreement between model-internal representations and human concepts, a \textbf{saliency-first privacy mechanism} sharing only thresholded attribution nodes, a bias-aware regularizer aligning subgroup statistics, and a Reveal-to-Revise loop integrating attribution signals into parameter updates without separate fine-tuning. Evaluated on CelebA, FairFace, Jigsaw, and HateXplain, our method achieves \textbf{94.1%} accuracy, \textbf{92.3%} macro F1, \textbf{79.4%} IoU-XAI, and \textbf{12.7} FID at 72--76% adversarial robustness, while reducing subgroup disparity $Δ_{\mathrm{bias}}$ by \textbf{41%}, demonstrating that mechanistic interpretability, fairness, and generative performance can be jointly optimized.

Medical decision systems increasingly rely on data from multiple sources to ensure reliable and unbiased diagnosis. However, existing multimodal learning models fail to achieve this goal because they often overlook two critical challenges. First, various data modalities may learn unevenly, thereby converging to a model biased towards certain modalities. Second, the model may emphasize learning on certain demographic groups causing unfair performances. The two aspects can influence each other, as different data modalities may favor respective groups during optimization, leading to both imbalanced and unfair multimodal learning. This paper proposes a novel approach called MultiFair for multimodal medical classification, which addresses these challenges with a dual-level gradient modulation process. MultiFair dynamically modulates training gradients regarding the optimization direction and magnitude at both data modality and group levels. We evaluate MultiFair on three real-world medical classification datasets with diverse demographic attributes,including multiclass classification and missing-modality settings. Experimental results demonstrate its effectiveness.

Discretizing raw features into bucketized attribute representations is a popular step before sharing a dataset. It is, however, evident that this step can cause significant bias in data and amplify unfairness in downstream tasks. In this paper, we address this issue by introducing the unbiased binning problem that, given an attribute to bucketize, finds its closest discretization to equal-size binning that satisfies group parity across different buckets. Defining a small set of boundary candidates, we prove that unbiased binning must select its boundaries from this set. We then develop an efficient dynamic programming algorithm on top of the boundary candidates to solve the unbiased binning problem. Finding an unbiased binning may sometimes result in a high price of fairness, or it may not even exist, especially when group values follow different distributions. Considering that a small bias in the group ratios may be tolerable in such settings, we introduce the epsilon-biased binning problem that bounds the group disparities across buckets to a small value epsilon. We first develop a dynamic programming solution, DP, that finds the optimal binning in quadratic time. The DP algorithm, while polynomial, does not scale to very large settings. Therefore, we propose a practically scalable algorithm, based on local search (LS), for epsilon-biased binning. The key component of the LS algorithm is a divide-and-conquer (D&C) algorithm that finds a near-optimal solution for the problem in near-linear time. We prove that D&C finds a valid solution for the problem unless none exists. The LS algorithm then initiates a local search, using the D&C solution as the upper bound, to find the optimal solution.

The high memory demands of generative language models have drawn attention to quantization, which reduces memory usage by mapping model weights to lower-precision integers. However, recent empirical studies show that, while efficient, quantization can increase the likelihood of generating biased outputs and degrade performance on fairness benchmarks. In this work, we draw new links between quantization and model fairness by adding explicit group-fairness constraints to the quantization objective and introduce Fair-GPTQ, the first quantization method explicitly designed to reduce unfairness in large language models. The added constraints guide the learning of the rounding operation toward less-biased text generation for protected groups. Specifically, we focus on stereotype generation involving occupational bias and discriminatory language spanning gender, race, and religion. Fair-GPTQ has minimal impact on performance, preserving at least 90% of baseline accuracy on zero-shot benchmarks, reduces unfairness relative to a half-precision model, and retains the memory and speed benefits of 4-bit quantization.

Prevalent multimodal self-supervised learning (SSL) methods rely on the redundancy assumption: that different views share substantial task-relevant information. We argue that this assumption fails in complex, real-world settings characterized by heterogeneity (e.g., variable-length healthcare or behavioral data), where enforcing strict alignment can discard unique, modality-specific signals and inadvertently amplify bias. In this work, we propose FairSSL, a framework that leverages data heterogeneity as a resource for fairness rather than a hindrance. Unlike standard contrastive approaches, FairSSL uses a subject-aware Variance-Invariance-Covariance Regularization objective, where alignment is enforced across segments drawn from the same subject. We introduce a segment-based pooling strategy to handle variable-length modalities, and we regularize representations to encourage (i) sufficient within-subject variability, (ii) cross-modal and cross-subject invariance, and (iii) representation decorrelation. Theoretical analysis shows that our objective bounds the score gap between protected groups. Empirically, FairSSL significantly outperforms existing baselines on heterogeneous multimodal datasets, improving fairness without sacrificing downstream predictive performance. Code available at: https://github.com/abtinmU/FairSSL

Machine learning models often preserve biases present in training data, leading to unfair treatment of certain minority groups. Despite an array of existing firm-side bias mitigation techniques, they typically incur utility costs and require organizational buy-in. Recognizing that many models rely on user-contributed data, end-users can induce fairness through the framework of Algorithmic Collective Action, where a coordinated minority group strategically relabels its own data to enhance fairness, without altering the firm's training process. We propose three practical, model-agnostic methods to approximate ideal relabeling and validate them on real-world datasets. Our findings show that a subgroup of the minority can substantially reduce unfairness with a small impact on the overall prediction error.

Federated learning (FL) allows collaborative training of machine learning models across multiple parties without sharing raw data. However, heterogeneous data can cause some clients to have disproportionate influence on the global model, leading to disparities in their performance. Fairness, understood as reducing these disparities, is therefore a crucial concern in FL and has been addressed in various ways. We studied performance equitable fairness in FL, where the goal is to minimize performance disparities across clients. We evaluated several existing fairness-aware methods and introduce here a new gradient-variance-regularized method, implemented in two variants: FairGrad (approximate) and FairGrad* (exact). We theoretically characterize the connections between these methods and, empirically, on heterogeneous benchmarks, show that FairGrad and FairGrad* consistently improve fairness by reducing variance in client accuracies, while maintaining competitive or improved mean performance compared to existing fairness-aware baselines.

Uncertainty in artificial intelligence (AI) predictions raises pressing legal and ethical questions for AI-assisted decision-making. This article examines two uncertainty-based algorithmic interventions that act as guardrails for human-AI interaction: selective abstention, which withholds high-uncertainty predictions from human decision-makers, and selective friction, which presents such predictions together with salient warnings about the model's uncertainty. Prior work suggests that uncertainty-based abstention can exacerbate disparities where under-represented groups are more likely to receive uncertain predictions. We provide, to our knowledge, the first doctrinal analysis of uncertainty-based algorithmic interventions under laws from the United Kingdom and examine their consequences through two AI-assisted case studies: consumer credit and risk of reoffending. We show that the use of uncertainty thresholds, though formally neutral, can generate discriminatory effects. We argue that both interventions pose risks of unlawful discrimination, but that selective friction is legally preferable. It preserves access to the prediction and is more likely to satisfy proportionality under the Equality Act 2010. Whether selective friction also improves decision quality in practice is uncertain. We identify conditions under which it may improve or worsen decision quality.

Fairness audits are a key component of responsible machine-learning deployment. Yet, audit-recommendation reliability under incomplete protected-label access is still poorly understood. In this work, we focused on protected-label missingness in fairness mitigation audits. We introduced a seed-calibrated stress test to separate missingness effects from seed-to-seed movement already present under complete labels. Across ACS/Folktables tasks, missingness settings that retain some protected labels usually do not move selected mitigation methods beyond a complete-label seed-to-seed baseline. At $0$ protected-label access, candidates collapse to an empirical-risk-minimization baseline and deterministic tie-breaking rather than revealing a broad missingness effect. We also found that threshold optimization can turn fairness gains on a single protected axis into intersectional harm above a seed baseline, and this threshold-optimizer finding persists under random-forest validation. Overall, our results highlight that protected-label missingness should be reported with seed-null calibration, candidate-set context, and intersectional consequences before it is treated as evidence of audit fragility.

Although recent large multimodal models (LMMs) show impressive progress on vision language tasks, their alignment with human centered (HC) principles such as fairness, ethics, inclusivity, empathy, and robustness is often overlooked. Existing LMM benchmarks are largely accuracy-agnostic. We present HumaniBench, a unified framework for characterizing HC alignment across realistic, socially grounded visual contexts. It contains 32,000 expert-verified image-question pairs from real-world news imagery, each mapped to one or more HC principles through explicit metrics. Comparing 15 state of the art LMMs reveals consistent trade -offs: proprietary systems lead on ethics, reasoning, and empathy, while open-source models show superior visual grounding and resilience. All models show persistent gaps in fairness and multilingual inclusivity. Chain-of-thought prompting and test-time scaling yield 8to 12 % gains on several HC dimensions. HumaniBench enables fine-grained analysis of alignment trade-offs not captured by conventional multimodal benchmarks. https://vectorinstitute.github.io/humanibench/

Fair machine learning seeks to identify and mitigate biases in predictions against unfavorable populations characterized by demographic attributes, such as race and gender. Recent research has extended fairness to graph data, such as social networks, but many studies neglect the causal relationships among data instances. This paper addresses a prevalent challenge in many fair machine learning research, which typically assumes independent and identically distributed (IID) data, from the causal perspective. Specifically, this work targets the circumstance where nodes with different neighborhood structures follow different causal mechanisms, violating the invariance assumptions required for classical structural causal models and do-calculus. We base our research on the Network Structural Causal Model (NSCM) framework and develop a Message Passing Variational Autoencoder for Causal Inference (MPVA) to compute interventional distributions for causally fair node classification. We establish theoretical soundness under two conditions: Decomposability and Graph Independence. These conditions formalize when causal mechanism heterogeneity can be overcome by constructing a structural representation that restores invariance and facilitates the computation of interventional distributions using do-calculus in non-IID settings. Empirical evaluations on semi-synthetic and real-world datasets demonstrate that MPVA outperforms conventional methods by effectively approximating interventional distributions and mitigating bias. Our findings demonstrate the potential of causality-based fairness in complex ML applications and motivate future work on relaxing the classic assumptions in algorithmic fairness.

Ensuring fairness is essential as machine learning increasingly informs consequential decisions. However, many fairness-aware methods focus on the outputs of individual predictors, without directly controlling sensitive information retained in the underlying representations. We propose Deep Fair Learning (DFL), which combines distance covariance regularization with predictive loss to jointly learn representations and downstream predictors, promoting fairness at both levels while preserving task-relevant information. Its marginal and class-conditional formulations target independence and separation, respectively. Under suitable regularity conditions, we establish non-asymptotic joint excess-risk rates and convergence of the learned representation up to natural invariances. We further derive fairness-inheritance bounds linking representation-level dependence to downstream disparities over suitable predictor classes, extending fairness guarantees beyond the jointly trained predictor. Experiments on tabular, text, and image benchmarks show that DFL achieves lower fairness gaps than competing methods in many evaluated settings while maintaining competitive predictive accuracy, with fairness gains largely preserved after downstream retraining.

Image classification models trained on clean data often degrade sharply when exposed to corrupted test or deployment data, such as images with impulse noise, Gaussian noise, or environmental noise. This degradation reduces overall performance and disproportionately affects demographic subgroups, raising algorithmic bias concerns. Although robust learning algorithms such as Sharpness-Aware Minimization improve overall robustness and generalization, they do not address biased performance degradation across demographic subgroups. Existing fairness-aware machine learning methods reduce performance disparities but struggle to maintain robust and equitable accuracy across demographic subgroups under data corruption. This limitation reveals an inherent tension between robustness and fairness under corrupted data. To address these challenges, we introduce a metric to assess performance degradation across subgroups under data corruption. We propose FairSAM, a framework that integrates Fairness-oriented strategies into SAM to equalize performance across demographic groups under corrupted conditions. Experiments on multiple real-world datasets and prediction tasks show that FairSAM balances robustness and fairness in corrupted image classification. The framework yields a structured solution for fair and robust image classification in the presence of data corruption.

Artificial intelligence (AI) has significantly improved medical screening accuracy, particularly in cancer detection and risk assessment. However, traditional classification metrics often fail to account for imbalanced data, varying performance across cohorts, and patient-level inconsistencies, leading to biased evaluations. We propose the cohort-attention evaluation metrics for tied data (CAT). CAT introduces patient-level assessment, entropy-based distribution weighting, and cohort-weighted sensitivity and specificity. Key metrics like CAT Sensitivity, CAT Specificity, and CAT Mean ensure balanced and fair evaluation across diverse populations. This approach enhances predictive reliability, fairness, and interpretability, providing a robust evaluation method for AI-driven medical screening models.

Large language models (LLMs) are increasingly used in high-stakes decisions such as hiring and college admissions, making their social bias a critical concern. While LLMs are trained to refuse explicitly biased requests, bias can be leaked implicitly during LLM planning and reasoning process. As code becomes the primary medium for LLM internal logic-writing, we introduce FairCoder, a benchmark that frames decision-making as coding tasks to systematically probe LLM bias across employment, education, and healthcare domains, covering multiple fairness definitions. Considering that existing metrics may fail when LLMs frequently refuse the request, we propose FairScore, a metric that jointly captures refusal behavior and group-level outcome diversity. Experiments with a 1k-sample dataset on powerful LLMs reveal consistent and previously underexplored bias patterns, such as prioritizing applicants from high-income families in college admissions. Our findings highlight the risks of deploying LLMs as decision-making agents and provide a comprehensive evaluation framework for future research.

Deep learning models exhibit fairness concerns when predictions are inadvertently influenced by sensitive attributes. However, existing attempts to make Path-Specific Counterfactual Fairness optimizable rely on estimating marginal potential outcome probabilities-an approach that fundamentally requires high-dimensional conditional density estimation and breaks down in modalities such as medical images, where the curse of dimensionality renders reliable estimation infeasible. To address this limitation, we reduce the problem of enforcing Path-Specific Counterfactual Fairness to a causal conditional independence constraint and prove that satisfying this constraint is sufficient to eliminate the unfair causal effect. This reduction replaces intractable counterfactual estimation with a discriminative optimization objective that remains scalable in high-dimensional settings.

This paper considers a novel variant of the online fair division problem involving multiple agents in which a learner sequentially observes an indivisible item that must be irrevocably allocated to one of the agents to achieve a desired balance between fairness and efficiency. Existing algorithms assume a small number of items with a sufficiently large number of copies, which ensures a good utility estimation for all item-agent pairs from noisy observed utilities. However, this assumption may not hold in many real-life applications, e.g., an online platform with a large number of users (items) who use the platform's service providers (agents) only a few times (a few copies of items), making it difficult to accurately estimate utilities for all item-agent pairs. To address this limitation, we assume utility is an unknown function of item-agent features. We propose algorithms that model online fair division as a contextual bandit problem and achieve provable sublinear regret. Our experimental results further validate the effectiveness of the proposed algorithms.

Fairness in decision-making processes is often quantified using probabilistic metrics. However, these metrics need not reflect the consequences of decisions for the affected individuals and groups. We develop a utility-based framework that incorporates these consequences into the assessment of fairness. Our main result shows that a decision-making process can satisfy $\varepsilon$-fairness while nevertheless being maximally unfair once the utilities associated with its outcomes are taken into account. To address applications in which information on false negatives is unavailable, we also formulate a reduced setting that retains the essential elements of the utility-based fairness assessment. We illustrate the framework through two applications: college admissions and credit-risk assessment. In both cases, probabilistic metrics may classify a decision-making process as approximately fair even though the corresponding utility outcomes are highly unequal. In the college-admissions example, our analysis shows that improving completion rates is necessary to achieve equality of utility across groups, while in the mortgage example, mitigating unfairness requires not only adjusting approval rates but also reducing the adverse consequences of default. These findings demonstrate that fairness assessments should account not only for the probabilities of different decisions but also for the consequences of those decisions.

Providing various machine learning (ML) applications in the real world, concerns about discrimination hidden in ML models are growing, particularly in high-stakes domains. Existing techniques for assessing the discrimination level of ML models include commonly used group and individual fairness measures. However, these two types of fairness measures are usually hard to be compatible, and even two different group fairness measures might be incompatible as well. To address this issue, we investigate and evaluate the discrimination level of classifiers from a manifold perspective and propose a fairness measure named harmonic fairness via manifolds (HFM)'' based on distances between sets. Yet the direct calculation of distances might be too expensive to afford, reducing its practical applicability. Therefore, we devise an approximation algorithm named Approximation of distance between sets (ApproxDist)'' to facilitate accurate estimation of distances, and we further demonstrate its algorithmic effectiveness under certain reasonable assumptions. Empirical results indicate that the proposed fairness measure HFM reflects bias from both individual and group fairness aspects and that the proposed ApproxDist is effective and efficient.

Deep neural networks are vulnerable to adversarial perturbations that can simultaneously degrade prediction robustness and individual fairness across diverse application settings. However, existing evaluation protocols typically assess these dimensions in isolation, thereby obscuring critical failure modes. To bridge this gap, we formalize Robust Individual Fairness (RIF): under semantic-preserving (truth-condition-preserving) perturbations, predictions should remain both correct with respect to the ground truth and invariant across semantically equivalent individuals. To surface RIF violations in practice, we introduce RIFair, a black-box adversarial framework that leverages a decoupled perturbation strategy to construct semantically preserved yet unrobust and/or unfair instance pairs. Experiments across multiple model architectures and real-world textual datasets show that robustness-only or fairness-only metrics often miss Robust Biased and Unrobust Fair behaviors. RIFair}reliably exposes these hidden vulnerabilities, supporting RIF as a necessary criterion for trustworthy model assessment. The experimental code is publicly available at https://github.com/Xuran-LI/RIFair.

Credit scoring has been catalogued by the European Commission and the Executive Office of the US President as a high-risk classification task, in light of the potential harms of making loan approval decisions based on models that would be biased against certain groups. To address this concern, recent credit scoring research has considered a range of fairness-enhancing techniques put forward by the machine learning community to reduce bias and unfair treatment in classification systems. While the definition of fairness or the approach they follow to impose it may vary, most of these techniques, however, disregard the robustness of the results. This can create situations where unfair treatment is effectively corrected in the training set, but when producing out-of-distribution classifications, unfair treatment is incurred again. Instead, in this paper, we will investigate how to apply Distributionally Robust Optimisation (DRO) methods to credit scoring, thereby empirically evaluating how they perform in terms of fairness, ability to classify correctly, and the robustness of the solution against changes in the marginal proportions. In so doing, we find DRO methods to provide a substantial improvement in terms of fairness, with almost no loss in predictive performance. These results thus indicate that DRO can improve fairness in credit scoring, provided that further advances are made in efficiently implementing these systems. In addition, our analysis suggests that many of the commonly used fairness metrics are not ideally suited to the credit scoring setting, as they evaluate performance at a single classification threshold.