We consider two-player games over finite graphs in which both players are restricted by fairness constraints on their moves. Given a two player game graph $G=(V,E)$ and a set of fair moves $E_f\subseteq E$ a player is said to play "fair" in $G$ if they choose an edge $e \in E_f$ infinitely often whenever the source vertex of $e$ is visited infinitely often. Otherwise, they play "unfair". We equip such games with two $ω$-regular winning conditions $α$ and $β$ deciding the winner of mutually fair and mutually unfair plays, respectively. Whenever one player plays fair and the other plays unfair, the fairly playing player wins the game. The resulting games are called "fair $α/β$ games". We formalize fair $α/β$ games and show that they are determined. For fair parity/parity games, i.e., fair $α/β$ games where $α$ and $β$ are given each by a parity condition over $G$, we provide a polynomial reduction to (normal) parity games via a gadget construction inspired by the reduction of stochastic parity games to parity games. We further give a direct symbolic fixpoint algorithm to solve fair parity/parity games. On a conceptual level, we illustrate the translation between the gadget-based redu
Machine learning models are increasingly deployed in high-stakes domains, raising concerns about both privacy and fairness. Differential Privacy (DP) has become a gold standard for privacy-preserving data analysis, while fairness-aware mechanisms aim to mitigate discrimination against underrepresented groups. However, these objectives can conflict: DP often amplifies disparities across demographic groups, and little is known about whether established fairness interventions remain effective under DP constraints. In this work, we present, to our knowledge, the first systematic evaluation of fairness interventions on differentially private synthetic tabular data. Our benchmark centers on the Adaptive Iterative Mechanism (AIM), identified as the state-of-the-art marginal-based DP synthesizer (Cormode et al. 2025). We thus evaluate fairness interventions across four datasets, multiple group fairness metrics, and three categories of mitigation strategies (pre-processing, in-processing, and post-processing) under a wide range of privacy budgets. We compare four pipeline configurations: (Baseline) training on original data; (DP-only) training on DP synthetic data; (Fair-only) applying fair
We present a post-processing algorithm for fair classification that covers group fairness criteria including statistical parity, equal opportunity, and equalized odds under a single framework, and is applicable to multiclass problems in both attribute-aware and attribute-blind settings. Our algorithm, called "LinearPost", achieves fairness post-hoc by linearly transforming the predictions of the (unfair) base predictor with a "fairness risk" according to a weighted combination of the (predicted) group memberships. It yields the Bayes optimal fair classifier if the base predictors being post-processed are Bayes optimal, otherwise, the resulting classifier may not be optimal, but fairness is guaranteed as long as the group membership predictor is multicalibrated. The parameters of the post-processing can be efficiently computed and estimated from solving an empirical linear program. Empirical evaluations demonstrate the advantage of our algorithm in the high fairness regime compared to existing post-processing and in-processing fair classification algorithms.
Clustering algorithms are widely used in many societal resource allocation applications, such as loan approvals and candidate recruitment, among others, and hence, biased or unfair model outputs can adversely impact individuals that rely on these applications. To this end, many fair clustering approaches have been recently proposed to counteract this issue. Due to the potential for significant harm, it is essential to ensure that fair clustering algorithms provide consistently fair outputs even under adversarial influence. However, fair clustering algorithms have not been studied from an adversarial attack perspective. In contrast to previous research, we seek to bridge this gap and conduct a robustness analysis against fair clustering by proposing a novel black-box fairness attack. Through comprehensive experiments, we find that state-of-the-art models are highly susceptible to our attack as it can reduce their fairness performance significantly. Finally, we propose Consensus Fair Clustering (CFC), the first robust fair clustering approach that transforms consensus clustering into a fair graph partitioning problem, and iteratively learns to generate fair cluster outputs. Experimen
Recent advances in generative models have sparked research on improving model fairness with AI-generated data. However, existing methods often face limitations in the diversity and quality of synthetic data, leading to compromised fairness and overall model accuracy. Moreover, many approaches rely on the availability of demographic group labels, which are often costly to annotate. This paper proposes AIM-Fair, aiming to overcome these limitations and harness the potential of cutting-edge generative models in promoting algorithmic fairness. We investigate a fine-tuning paradigm starting from a biased model initially trained on real-world data without demographic annotations. This model is then fine-tuned using unbiased synthetic data generated by a state-of-the-art diffusion model to improve its fairness. Two key challenges are identified in this fine-tuning paradigm, 1) the low quality of synthetic data, which can still happen even with advanced generative models, and 2) the domain and bias gap between real and synthetic data. To address the limitation of synthetic data quality, we propose Contextual Synthetic Data Generation (CSDG) to generate data using a text-to-image diffusion
With the emerging needs of creating fairness-aware solutions for search and recommendation systems, a daunting challenge exists of evaluating such solutions. While many of the traditional information retrieval (IR) metrics can capture the relevance, diversity, and novelty for the utility with respect to users, they are not suitable for inferring whether the presented results are fair from the perspective of responsible information exposure. On the other hand, existing fairness metrics do not account for user utility or do not measure it adequately. To address this problem, we propose a new metric called FAIR. By unifying standard IR metrics and fairness measures into an integrated metric, this metric offers a new perspective for evaluating fairness-aware ranking results. Based on this metric, we developed an effective ranking algorithm that jointly optimized user utility and fairness. The experimental results showed that our FAIR metric could highlight results with good user utility and fair information exposure. We showed how FAIR related to a set of existing utility and fairness metrics and demonstrated the effectiveness of our FAIR-based algorithm. We believe our work opens up a
Medical AI faces challenges in privacy-preserving collaborative learning while ensuring fairness across heterogeneous healthcare institutions. Current federated learning approaches suffer from static architectures, slow convergence (45-73 rounds), fairness gaps marginalizing smaller institutions, and scalability constraints (15-client limit). We propose Adaptive Fair Federated Learning (AFFL) through three innovations: (1) Adaptive Knowledge Messengers dynamically scaling capacity based on heterogeneity and task complexity, (2) Fairness-Aware Distillation using influence-weighted aggregation, and (3) Curriculum-Guided Acceleration reducing rounds by 60-70%. Our theoretical analysis provides convergence guarantees with epsilon-fairness bounds, achieving O(T^{-1/2}) + O(H_max/T^{3/4}) rates. Projected results show 55-75% communication reduction, 56-68% fairness improvement, 34-46% energy savings, and 100+ institution support. The framework enables multi-modal integration across imaging, genomics, EHR, and sensor data while maintaining HIPAA/GDPR compliance. We propose MedFedBench benchmark suite for standardized evaluation across six healthcare dimensions: convergence efficiency, ins
This Conceptual Design Report (CDR) presents the plans of the computing infrastructure for research at FAIR, Darmstadt, Germany. It presents the computing requirements of the various research groups, the policies for the computing and storage infrastructure, the foreseen FAIR computing model including the open data, software and services policies and architecture for the periods starting in 2028 with the "first science (plus)" phase to the modularized start version of FAIR. The overall ambition is to create a federated and centrally-orchestrated infrastructure serving the large diversity of the research lines present with sufficient scalability and flexibility to cope with future data challenges that will be present at FAIR.
This paper describes a differentially private post-processing algorithm for learning fair regressors satisfying statistical parity, addressing privacy concerns of machine learning models trained on sensitive data, as well as fairness concerns of their potential to propagate historical biases. Our algorithm can be applied to post-process any given regressor to improve fairness by remapping its outputs. It consists of three steps: first, the output distributions are estimated privately via histogram density estimation and the Laplace mechanism, then their Wasserstein barycenter is computed, and the optimal transports to the barycenter are used for post-processing to satisfy fairness. We analyze the sample complexity of our algorithm and provide fairness guarantee, revealing a trade-off between the statistical bias and variance induced from the choice of the number of bins in the histogram, in which using less bins always favors fairness at the expense of error.
Before a fair exchange takes place, there is typically an advertisement phase with the goal of increasing the appeal of possessing a digital asset while keeping it sufficiently hidden. Advertisement phases are implicit in mainstream definitions, and therefore are not explicitly integrated within fair-exchange protocols. In this work we give an explicit definition for such a fair exchange in a setting where parties communicate via broadcast messages only (i.e., no point-to-point connection between seller and buyer is needed). Next, we construct a fair-exchange protocol satisfying our new definition using zk-SNARKs and relying on mainstream decentralized platforms (i.e., a blockchain with smart contracts like Ethereum and a decentralized storage system like IPFS). Experimental results confirm the practical relevance of our decentralized approach, paving the road towards building decentralized marketplaces where users can, even anonymously, and without direct off-chain communications, effectively advertise and exchange their digital assets as part of a system of enhanced NFTs.
Ensuring fairness of prediction-based decision making is based on statistical group fairness criteria. Which one of these criteria is the morally most appropriate one depends on the context, and its choice requires an ethical analysis. In this paper, we present a step-by-step procedure integrating three elements: (a) a framework for the moral assessment of what fairness means in a given context, based on the recently proposed general principle of "Fair equality of chances" (FEC) (b) a mapping of the assessment's results to established statistical group fairness criteria, and (c) a method for integrating the thus-defined fairness into optimal decision making. As a second contribution, we show new applications of the FEC principle and show that, with this extension, the FEC framework covers all types of group fairness criteria: independence, separation, and sufficiency. Third, we introduce an extended version of the FEC principle, which additionally allows accounting for morally irrelevant elements of the fairness assessment and links to well-known relaxations of the fairness criteria. This paper presents a framework to develop fair decision systems in a conceptually sound way, combi
Weak gravitational lensing, the correlated distortion of background galaxy shapes by foreground structures, is a powerful probe of the matter distribution in our universe and allows accurate constraints on the cosmological model. In recent years, high-order statistics and machine learning (ML) techniques have been applied to weak lensing data to extract the nonlinear information beyond traditional two-point analysis. However, these methods typically rely on cosmological simulations, which poses several challenges: simulations are computationally expensive, limiting most realistic setups to a low training data regime; inaccurate modeling of systematics in the simulations create distribution shifts that can bias cosmological parameter constraints; and varying simulation setups across studies make method comparison difficult. To address these difficulties, we present the first weak lensing benchmark dataset with several realistic systematics and launch the FAIR Universe Weak Lensing Machine Learning Uncertainty Challenge. The challenge focuses on measuring the fundamental properties of the universe from weak lensing data with limited training set and potential distribution shifts, whi
The translation of gender-neutral person-referring terms (e.g., the students) is often non-trivial. Translating from English into German poses an interesting case -- in German, person-referring nouns are usually gender-specific, and if the gender of the referent(s) is unknown or diverse, the generic masculine (die Studenten (m.)) is commonly used. This solution, however, reduces the visibility of other genders, such as women and non-binary people. To counteract gender discrimination, a societal movement towards using gender-fair language exists (e.g., by adopting neosystems). However, gender-fair German is currently barely supported in machine translation (MT), requiring post-editing or manual translations. We address this research gap by studying gender-fair language in English-to-German MT. Concretely, we enrich a community-created gender-fair language dictionary and sample multi-sentence test instances from encyclopedic text and parliamentary speeches. Using these novel resources, we conduct the first benchmark study involving two commercial systems and six neural MT models for translating words in isolation and natural contexts across two domains. Our findings show that most sy
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 has to be irrevocably allocated to one of the agents while satisfying a fairness and efficiency constraint. 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 bandit feedback. However, this assumption may not hold in many real-life applications, for example, an online platform that has a large number of users (items) who use the platform's service providers (agents) only a few times (a few copies of items), which makes it difficult to accurately estimate utilities for all item-agent pairs. To address this, we assume utility is an unknown function of item-agent features. We then propose algorithms that model online fair division as a contextual bandit problem, with sub-linear regret guarantees. Our experimental results further validate the effectiveness of the proposed algorithms.
Conversational AI has significant potential in the healthcare sector, but many existing systems fall short in emotional intelligence, fairness, and politeness, which are essential for building patient trust. This gap reduces the effectiveness of digital health solutions and can increase user anxiety. This study addresses the challenge of integrating ethical communication principles by designing and evaluating LunaAI, a healthcare chatbot prototype. Using a user-centered design approach informed by a structured literature review, we developed conversational scenarios that handle both routine and hostile user interactions. The system was implemented using the Google Gemini API and deployed as a mobile-first Progressive Web App built with React, Vite, and Firebase. Preliminary user testing was conducted with a small participant group, and responses were evaluated using established frameworks such as the Godspeed Questionnaire. In addition, a comparative analysis was performed between LunaAI's tailored responses and the baseline outputs of an uncustomized large language model. The results indicate measurable improvements in key interaction qualities, with average user ratings of 4.7 ou
Ensuring fairness is essential for every education system. Machine learning is increasingly supporting the education system and educational data science (EDS) domain, from decision support to educational activities and learning analytics. However, the machine learning-based decisions can be biased because the algorithms may generate the results based on students' protected attributes such as race or gender. Clustering is an important machine learning technique to explore student data in order to support the decision-maker, as well as support educational activities, such as group assignments. Therefore, ensuring high-quality clustering models along with satisfying fairness constraints are important requirements. This chapter comprehensively surveys clustering models and their fairness in EDS. We especially focus on investigating the fair clustering models applied in educational activities. These models are believed to be practical tools for analyzing students' data and ensuring fairness in EDS.
Arguments for the FAIR principles have mostly been based on appeals to values. However, the work of onboarding diverse researchers to make efficient and effective implementations of FAIR requires different appeals. In our recent effort to transform the institution into a FAIR University by 2025, here we report on the experiences of the Community of Data Driven Insights (CDDI). We describe these experiences from the perspectives of a data steward in social sciences and a data scientist, both of whom have been working in parallel to provide research data management and data science support to different research groups. We initially identified 5 challenges for FAIR implementation. These perspectives show the complex dimensions of FAIR implementation to researchers across disciplines in a single university.
The real-time data processing of the next generation of experiments conducted at FAIR requires a reliable reconstruction of event topologies and, therefore, will depend heavily on in-situ calibration procedures. A neural network-based approach can provide fast real-time calibrations based on continuously available environmental data. We applied this approach to the data obtained from the Drift Chambers of HADES. To enhance regularization we incorporate information about previous environmental states into the Long Short-Term Memory (LSTM) architecture and combine it with Graph Convolutions to account for correlations between different chambers. With the usage of a proposed prediction strategy we achieved stable and accurate predictions, matching the quality of an offline calibration. Moreover, our approach significantly reduces the calibration time, making it well-suited for real-time applications within high-rate data acquisition environments.
Binary decision making classifiers are not fair by default. Fairness requirements are an additional element to the decision making rationale, which is typically driven by maximizing some utility function. In that sense, algorithmic fairness can be formulated as a constrained optimization problem. This paper contributes to the discussion on how to implement fairness, focusing on the fairness concepts of positive predictive value (PPV) parity, false omission rate (FOR) parity, and sufficiency (which combines the former two). We show that group-specific threshold rules are optimal for PPV parity and FOR parity, similar to well-known results for other group fairness criteria. However, depending on the underlying population distributions and the utility function, we find that sometimes an upper-bound threshold rule for one group is optimal: utility maximization under PPV parity (or FOR parity) might thus lead to selecting the individuals with the smallest utility for one group, instead of selecting the most promising individuals. This result is counter-intuitive and in contrast to the analogous solutions for statistical parity and equality of opportunity. We also provide a solution for
Training classifiers under fairness constraints such as group fairness, regularizes the disparities of predictions between the groups. Nevertheless, even though the constraints are satisfied during training, they might not generalize at evaluation time. To improve the generalizability of fair classifiers, we propose fair mixup, a new data augmentation strategy for imposing the fairness constraint. In particular, we show that fairness can be achieved by regularizing the models on paths of interpolated samples between the groups. We use mixup, a powerful data augmentation strategy to generate these interpolates. We analyze fair mixup and empirically show that it ensures a better generalization for both accuracy and fairness measurement in tabular, vision, and language benchmarks.