Algorithmic Fairness

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.

This PhD thesis investigates the societal impact of machine learning (ML). ML increasingly informs consequential decisions and recommendations, significantly affecting many aspects of our lives. As these data-driven systems are often developed without explicit fairness considerations, they carry the risk of discriminatory effects. The contributions in this thesis enable more appropriate measurement of fairness in ML systems, systematic decomposition of ML systems to anticipate bias dynamics, and effective interventions that reduce algorithmic discrimination while maintaining system utility. I conclude by discussing ongoing challenges and future research directions as ML systems, including generative artificial intelligence, become increasingly integrated into society. This work offers a foundation for ensuring that ML's societal impact aligns with broader social values.

We treat the internals of generative models as mechanistic objects rather than black boxes. We introduce Attribution Graphs (AGs), which extend GradCAM++ to circuit-level representations, and 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 Cognitive Alignment Score (CAS), quantifying agreement between model-internal representations and human concepts, a 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 94.1% accuracy, 92.3% macro F1, 79.4% IoU-XAI, and 12.7 FID at 72--76% adversarial robustness, while reducing subgroup disparity $Δ_{\mathrm{bias}}$ by 41%, demonstrating that mechanistic interpretability, fairness, and generative performance can be jointly optimized.

Large language models (LLMs) are increasingly under scrutiny for perpetuating identity-based discrimination in high-stakes domains such as hiring, particularly against people with disabilities (PwD). However, existing research remains largely Western-centric, overlooking how intersecting forms of marginalization--such as gender and caste--shape experiences of PwD in the Global South. We conduct a comprehensive audit of six LLMs across 2,820 hiring scenarios spanning diverse disability, gender, nationality, and caste profiles. To capture subtle intersectional harms and biases, we introduce ABLEIST (Ableism, Inspiration, Superhumanization, and Tokenism), a set of five ableism-specific and three intersectional harm metrics grounded in disability studies literature. Our results reveal significant increases in ABLEIST harms towards disabled candidates--harms that many state-of-the-art models failed to detect. These harms were further amplified by sharp increases in intersectional harms (e.g., Tokenism) for gender and caste-marginalized disabled candidates, highlighting critical blind spots in current safety tools and the need for intersectional safety evaluations of frontier models in high-stakes domains like hiring.

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.

We study fairness-accuracy tradeoffs when a single predictive model must serve multiple demographic groups. A useful tool for understanding this tradeoff is the fairness-accuracy (FA) Pareto frontier, which characterizes the set of models that cannot be improved in either fairness or accuracy without worsening the other. While characterizing the FA frontier requires full knowledge of the data distribution, we focus on the finite-sample regime, quantifying how well a designer can approximate any point on the frontier from limited data and bounding the worst-case gap. In particular, we derive worst-case-optimal estimators that depend on the designer's knowledge of the covariate distribution. For each estimator, we characterize how finite-sample effects asymmetrically impact each group's welfare and identify optimal sample allocation strategies. Finally, we provide uniform finite-sample bounds along the entire FA frontier, quantifying finite-sample deviations across alternative fairness-accuracy tradeoffs.

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.

We revisit the foundations of fairness and its interplay with utility and efficiency in settings where the training data contain richer labels, such as individual types, rankings, or risk estimates, rather than just binary outcomes. In this context, we propose algorithms that achieve stronger notions of evidence-based fairness than are possible in standard supervised learning. Our methods support classification and ranking techniques that preserve accurate subpopulation classification rates, as suggested by the underlying data distributions, across a broad class of classification rules and downstream applications. Furthermore, our predictors enable loss minimization, whether aimed at maximizing utility or in the service of fair treatment. Complementing our algorithmic contributions, we present impossibility results demonstrating that simultaneously achieving accurate classification rates and optimal loss minimization is, in some cases, computationally infeasible. Unlike prior impossibility results, our notions are not inherently in conflict and are simultaneously satisfied by the Bayes-optimal predictor. Furthermore, we show that each notion can be satisfied individually via efficient learning. Our separation thus stems from the computational hardness of learning a sufficiently good approximation of the Bayes-optimal predictor. These computational impossibilities present a choice between two natural and attainable notions of accuracy that could both be motivated by fairness.

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.

While machine learning fairness has made significant progress in recent years, most existing solutions focus on tabular data and are poorly suited for vision-based classification tasks, which rely heavily on deep learning. To bridge this gap, we introduce DetoxAI, an open-source Python library for improving fairness in deep learning vision classifiers through post-hoc debiasing. DetoxAI implements state-of-the-art debiasing algorithms, fairness metrics, and visualization tools. It supports debiasing via interventions in internal representations and includes attribution-based visualization tools and quantitative algorithmic fairness metrics to show how bias is mitigated. This paper presents the motivation, design, and use cases of DetoxAI, demonstrating its tangible value to engineers and researchers.

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.

As algorithmic decision making has become increasingly ubiquitous even in high-stakes settings, significant effort has been invested in defining, detecting, and eliminating unfair model-driven outcomes. Prior work has largely focused on estimating the fairness properties of a given predictive model, and quantifying uncertainty based on variability in a fixed model's performance across evaluation datasets. Alternatively, we can also ask about uncertainty that the model inherits from its training data; here we evaluate data fairness - fairness in the data generating process used for training. We perform inference on data fairness using targeted learning, a flexible framework for nonparametric inference, and derive estimators for demographic parity, equal opportunity, and conditional mutual information. Simulations show that our data fairness estimators improve confidence-interval coverage and reduce false detections of population unfairness relative to fixed-model inference. We also demonstrate their application to real data.

Freezing of gait (FOG) is a debilitating feature of Parkinson's disease (PD) and a common cause of injurious falls. Recent advances in wearable-based human activity recognition (HAR) have enabled FOG detection, but bias and fairness in these models remain understudied. Bias is defined as a systematic error leading to unequal outcomes, while fairness refers to consistent performance across subject groups. Biased models could systematically underserve patients with specific FOG phenotypes or demographics, widening care disparities. We evaluated the bias and fairness of state-of-the-art HAR models for FOG detection across FOG phenotypes and patient demographics using 4 public wearable datasets (145 subjects and 59.8 hours of recording) with multiple on-body sensor locations and temporal annotations on FOG episodes across various behavioral test protocols. Four mitigation approaches were assessed: conventional methods (threshold optimization and adversarial debiasing) and two transfer learning-based approaches (multi-site transfer and fine-tuning pre-trained models). Fairness was primarily quantified using the demographic parity ratio (DPR) and the equalized odds ratio (EOR). HAR models exhibited substantial bias (DPR & EOR < 0.8) across age, sex, disease duration, and critically, FOG phenotype. This phenotype-specific bias is particularly concerning as tremulous and akinetic FOG may require different clinical management. Conventional methods failed: threshold optimization (DPR=-0.126, EOR=+0.063) and adversarial debiasing (DPR=-0.008, EOR=-0.001). In contrast, multi-site transfer learning improved fairness (DPR=+0.037, p<0.01; EOR=+0.045, p<0.01) and performance (F1-score=+0.020, p<0.05), though neither metric reached 0.8. Transfer learning across diverse datasets may partially mitigate these disparities, helping wearable-based FOG monitoring benefit all individuals with PD.

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.

Machine learning systems are increasingly being used in critical decision making such as healthcare, finance, and criminal justice. Concerns around their fairness have resulted in several bias mitigation techniques that emphasize the need for high-quality data to ensure fairer decisions. However, the role of earlier stages of machine learning pipelines in mitigating model bias has not been explored well. In this paper, we focus on the task of acquiring additional labeled data points for training the downstream machine learning model to rapidly improve its fairness. Since not all data points in a data pool are equally beneficial to the task of fairness, we generate an ordering in which data points should be acquired. We present DataSift, a data acquisition framework based on the idea of data valuation that relies on partitioning and multi-armed bandits to determine the most valuable data points to acquire. Over several iterations, DataSift selects a partition and randomly samples a batch of data points from the selected partition, evaluates the benefit of acquiring the batch on model fairness, and updates the utility of partitions depending on the benefit. To further improve the effectiveness and efficiency of evaluating batches, we leverage influence functions that estimate the effect of acquiring a batch without retraining the model. We empirically evaluate DataSift on several real-world and synthetic datasets and show that the fairness of a machine learning model can be significantly improved even while acquiring a few data points.

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.