Papers

Field

Activity · 12 weeks

Recent papers

All papers in Research

arXiv cs.LGOct 30
A Framework for Task-Agnostic Counterfactual Fairness in Transformers through Activation Steering
Joshua Wolff Anderson, Yanshan Wang, Shyam Visweswaran
Bias in transformer-based models is a growing concern as these architectures become more prevalent in automated decision-making systems, such as prediction models for hiring, lending, and clinical treatment recommendation. Mechanistic interpretability (MI) is a growing body of work that measures meaningful causal effects of activations on model output by identifying human-interpretable features encoded in model activations. When such features correspond to sensitive attributes, they provide a direct way to quantify the bias those attributes introduce and to causally intervene to mitigate it. However, counterfactual fairness (CF) methods have not been systematically adapted to this setting of intervening on interpretable mechanisms in transformers. We propose a framework, Mechanistic Interpretability for Counterfactual Fairness (MICF), that utilizes MI tools to reformulate CF constraints in terms of transformer activations, unifying former approaches into a single pipeline for fairness analysis in transformers. MICF does not require a prior causal model or specific transformer architecture. We evaluate MICF on real-world tabular data and show that CF can be improved across…
PDF arXiv
arXiv cs.LGOct 30
KINDER: Kernel-based Independence for Fair Representation Learning via Prototype-space Erasure
Abtin Mogharabin, Alp Toykan Kaplan, Jiaee Cheong, Sinan Kalkan
Concept erasure is a prominent approach to achieving fairness in machine learning through the removal of sensitive attributes from learned representations. Prior concept erasure methods typically define debiasing indirectly through the failure of a chosen adversary, probe, or fairness penalty, which makes the target of erasure dependent on a particular decoder family or optimization setup. We introduce KINDER, which directly removes sensitive-attribute information from intermediate representations with respect to a chosen family of prototype functionals, and is compatible with any deep model containing an intermediate feature space, independent of the architecture, task type, or training paradigm. KINDER operates in a random Fourier feature space, where it estimates a sensitive subspace from protected group prototypes and projects representations onto its orthogonal complement. Thus, it forms an explicit representation cleaning mechanism distinct from prior fairness control studies. We conduct extensive experiments across diverse settings and show the effectiveness of KINDER on (i) supervised and self-supervised settings, (ii) classification, regression, and image segmentation…
PDF arXiv
arXiv stat.MLOct 29
Hidden Disparities in Ranking: Category-Aware Fairness via Distributional Stability
Gayane Taturyan, Charlotte Laclau, Stephan Clémençon
We study the problem of fair ranking in recommender systems. We provide a formal probabilistic framework in which ranking policies are distributions over permutations, and the utility of a user is the exposure given to the items they interact with, relative to that of an ideal ranking. We consider utility parity across user groups, as well as its category-aware refinement, conditional utility parity, which requires parity within each category of items. Following a recent view of fairness as distributional stability, we show that both criteria are equivalent to the stability of the utility under changes in the composition of user groups. Optimizing over mixtures of ranking policies leads to a second-order cone program, for which we provide generalization bounds. A numerical study validates our theoretical findings.
PDF arXiv
arXiv cs.LGOct 28
FairSplit: Decomposing the Embedding Space for Fair Classification
Andrii Shkabrii, Anna Beer, Ylli Sadikaj, Claudia Plant
Fair classification faces a twofold challenge: maintaining high classification accuracy while limiting reliance on sensitive information. Our method FairSplit achieves this by learning a decomposition of the embedding space into a Fair Space used for prediction and a Sensitive Space that isolates sensitive information. During training, the model must simultaneously learn the classification task and separate fair from sensitive information. The Sensitive Space gives sensitive attributes a destination, so the Fair Space can be used for prediction without relying on them. This decomposition is guided via a learnable mask and the Hilbert-Schmidt Independence Criterion (HSIC) as a measure of statistical dependence. We provide theoretical guarantees showing that the demographic parity gap is upper-bounded by both (i) the learned dimensionality of the Fair Space and (ii) the HSIC between the Fair Space and sensitive attributes. FairSplit effectively handles multiclass tasks and non-binary sensitive attributes, overcoming key limitations of existing fair classification methods. Experiments on established fairness benchmarks show that FairSplit achieves competitive accuracy-fairness…
PDF arXiv
arXiv cs.LGOct 27
Integral Probability Boundaries
Bogdan Kulynych, Shahab Asoodeh
Bounds based on Integral Probability Metrics (IPMs) are ubiquitous in machine learning and statistics, appearing, e.g., in generalization, alignment, fairness, and privacy. IPMs reduce the discrepancy between two distributions to a single worst-case gap between expectations. This compression is costly: for rare events, safety failures, or under-represented groups, IPM-based bounds are loose or vacuous. We introduce a non-linear generalization of IPMs, which we term Integral Probability Boundaries (IPBs). Unlike IPMs, IPBs provide bounds that are tight at the extremes. We derive their basic properties and present algorithms for estimating them in practically relevant settings. We demonstrate the usage of IPBs in both theoretical and practical applications for alignment, judge-free performance estimation, and fairness, where they enable us to obtain sharp bounds on performance and fairness gaps, e.g., 15 p.p. more precise estimates on fairness gaps for rare groups in a realistic generative modeling task, compared to the state of the art.
PDF arXiv
arXiv cs.AIOct 27
Algorithmic Bias from the Perspectives of Healthcare Professionals
Jennifer Xu, Tamara Babaian
This paper focuses on algorithmic bias of machine learning and artificial intelligence applications in healthcare information systems. Based on the quantitative data and qualitative comments from a survey and interviews with healthcare professionals, who have different job roles (e.g., clinical vs. administrative), this study provides findings about the relationships between algorithmic bias, perceived fairness, and the intended acceptance and adoption of ML algorithms and algorithm generated outcomes. The results suggest that the opinions of healthcare professionals toward the causes of algorithmic bias, the criteria of algorithm assessment, the perceived fairness, and bias mitigation approaches may vary depending on their job roles, perspectives, tasks, and the algorithm characteristics. More research is needed to investigate algorithmic bias to ensure fairness and equality in healthcare.
PDF arXiv

Papers

Topics in this field

algorithmic fairness · fairness constraints · fairness aware68 papers7 this week

Fields · AI · updated 15m ago

Algorithmic fairness

Found by the topic model: algorithmic fairness.

7papers this week−36.4% vs last week

All papers · 68 With code · 0

Newest Most relevant

39 papers this month

Recent papers

All papers in Research

arXiv cs.LGOct 30
A Framework for Task-Agnostic Counterfactual Fairness in Transformers through Activation Steering
Joshua Wolff Anderson, Yanshan Wang, Shyam Visweswaran
Bias in transformer-based models is a growing concern as these architectures become more prevalent in automated decision-making systems, such as prediction models for hiring, lending, and clinical treatment recommendation. Mechanistic interpretability (MI) is a growing body of work that measures meaningful causal effects of activations on model output by identifying human-interpretable features encoded in model activations. When such features correspond to sensitive attributes, they provide a direct way to quantify the bias those attributes introduce and to causally intervene to mitigate it. However, counterfactual fairness (CF) methods have not been systematically adapted to this setting of intervening on interpretable mechanisms in transformers. We propose a framework, Mechanistic Interpretability for Counterfactual Fairness (MICF), that utilizes MI tools to reformulate CF constraints in terms of transformer activations, unifying former approaches into a single pipeline for fairness analysis in transformers. MICF does not require a prior causal model or specific transformer architecture. We evaluate MICF on real-world tabular data and show that CF can be improved across…
PDF arXiv
arXiv cs.LGOct 30
KINDER: Kernel-based Independence for Fair Representation Learning via Prototype-space Erasure
Abtin Mogharabin, Alp Toykan Kaplan, Jiaee Cheong, Sinan Kalkan
Concept erasure is a prominent approach to achieving fairness in machine learning through the removal of sensitive attributes from learned representations. Prior concept erasure methods typically define debiasing indirectly through the failure of a chosen adversary, probe, or fairness penalty, which makes the target of erasure dependent on a particular decoder family or optimization setup. We introduce KINDER, which directly removes sensitive-attribute information from intermediate representations with respect to a chosen family of prototype functionals, and is compatible with any deep model containing an intermediate feature space, independent of the architecture, task type, or training paradigm. KINDER operates in a random Fourier feature space, where it estimates a sensitive subspace from protected group prototypes and projects representations onto its orthogonal complement. Thus, it forms an explicit representation cleaning mechanism distinct from prior fairness control studies. We conduct extensive experiments across diverse settings and show the effectiveness of KINDER on (i) supervised and self-supervised settings, (ii) classification, regression, and image segmentation…
PDF arXiv
arXiv stat.MLOct 29
Hidden Disparities in Ranking: Category-Aware Fairness via Distributional Stability
Gayane Taturyan, Charlotte Laclau, Stephan Clémençon
We study the problem of fair ranking in recommender systems. We provide a formal probabilistic framework in which ranking policies are distributions over permutations, and the utility of a user is the exposure given to the items they interact with, relative to that of an ideal ranking. We consider utility parity across user groups, as well as its category-aware refinement, conditional utility parity, which requires parity within each category of items. Following a recent view of fairness as distributional stability, we show that both criteria are equivalent to the stability of the utility under changes in the composition of user groups. Optimizing over mixtures of ranking policies leads to a second-order cone program, for which we provide generalization bounds. A numerical study validates our theoretical findings.
PDF arXiv
arXiv cs.LGOct 28
FairSplit: Decomposing the Embedding Space for Fair Classification
Andrii Shkabrii, Anna Beer, Ylli Sadikaj, Claudia Plant
Fair classification faces a twofold challenge: maintaining high classification accuracy while limiting reliance on sensitive information. Our method FairSplit achieves this by learning a decomposition of the embedding space into a Fair Space used for prediction and a Sensitive Space that isolates sensitive information. During training, the model must simultaneously learn the classification task and separate fair from sensitive information. The Sensitive Space gives sensitive attributes a destination, so the Fair Space can be used for prediction without relying on them. This decomposition is guided via a learnable mask and the Hilbert-Schmidt Independence Criterion (HSIC) as a measure of statistical dependence. We provide theoretical guarantees showing that the demographic parity gap is upper-bounded by both (i) the learned dimensionality of the Fair Space and (ii) the HSIC between the Fair Space and sensitive attributes. FairSplit effectively handles multiclass tasks and non-binary sensitive attributes, overcoming key limitations of existing fair classification methods. Experiments on established fairness benchmarks show that FairSplit achieves competitive accuracy-fairness…
PDF arXiv
arXiv cs.LGOct 27
Integral Probability Boundaries
Bogdan Kulynych, Shahab Asoodeh
Bounds based on Integral Probability Metrics (IPMs) are ubiquitous in machine learning and statistics, appearing, e.g., in generalization, alignment, fairness, and privacy. IPMs reduce the discrepancy between two distributions to a single worst-case gap between expectations. This compression is costly: for rare events, safety failures, or under-represented groups, IPM-based bounds are loose or vacuous. We introduce a non-linear generalization of IPMs, which we term Integral Probability Boundaries (IPBs). Unlike IPMs, IPBs provide bounds that are tight at the extremes. We derive their basic properties and present algorithms for estimating them in practically relevant settings. We demonstrate the usage of IPBs in both theoretical and practical applications for alignment, judge-free performance estimation, and fairness, where they enable us to obtain sharp bounds on performance and fairness gaps, e.g., 15 p.p. more precise estimates on fairness gaps for rare groups in a realistic generative modeling task, compared to the state of the art.
PDF arXiv
arXiv cs.AIOct 27
Algorithmic Bias from the Perspectives of Healthcare Professionals
Jennifer Xu, Tamara Babaian
This paper focuses on algorithmic bias of machine learning and artificial intelligence applications in healthcare information systems. Based on the quantitative data and qualitative comments from a survey and interviews with healthcare professionals, who have different job roles (e.g., clinical vs. administrative), this study provides findings about the relationships between algorithmic bias, perceived fairness, and the intended acceptance and adoption of ML algorithms and algorithm generated outcomes. The results suggest that the opinions of healthcare professionals toward the causes of algorithmic bias, the criteria of algorithm assessment, the perceived fairness, and bias mitigation approaches may vary depending on their job roles, perspectives, tasks, and the algorithm characteristics. More research is needed to investigate algorithmic bias to ensure fairness and equality in healthcare.
PDF arXiv

Active contributors · 90 days

Charlotte LaclauHidden Disparities in Ranking: Category-Aware Fairness via Distributional Stability2
Gayane TaturyanHidden Disparities in Ranking: Category-Aware Fairness via Distributional Stability2
Deevesh JainFYC: FPR-Disparity Weight Perturbation and Youden Calibration for Fair Deepfake Detection2
Taiwo OlabamipeFYC: FPR-Disparity Weight Perturbation and Youden Calibration for Fair Deepfake Detection2
Uzoamaka EzeakunneFYC: FPR-Disparity Weight Perturbation and Youden Calibration for Fair Deepfake Detection2
Xiuwen LiuFYC: FPR-Disparity Weight Perturbation and Youden Calibration for Fair Deepfake Detection2