An official website of the United States government
Fair representations are a powerful tool for establishing criteria like statistical parity, proxy non-discrimination, and equality of opportunity in learned models. Existing techniques for learning these representations are typically model-agnostic, as they preprocess the original data such that the output satisfies some fairness criterion, and can be used with arbitrary learning methods. In contrast, we demonstrate the promise of learning a model-aware fair representation, focusing on kernel-based models. We leverage the classical Sufficient Dimension Reduction (SDR) framework to construct representations as subspaces of the reproducing kernel Hilbert space (RKHS), whose member functions are guaranteed to satisfy fairness. Our method supports several fairness criteria, continuous and discrete data, and multiple protected attributes. We further show how to calibrate the accuracy tradeoff by characterizing it in terms of the principal angles between subspaces of the RKHS. Finally, we apply our approach to obtain the first Fair Gaussian Process (FGP) prior for fair Bayesian learning, and show that it is competitive with, and in some cases outperforms, state-of-the-art methods on real data.
more »
« less
Kernel Multiaccuracy
Predefined demographic groups often overlook the subpopulations most impacted by model errors, leading to a growing emphasis on data-driven methods that pinpoint where models underperform. The emerging field of multi-group fairness addresses this by ensuring models perform well across a wide range of group-defining functions, rather than relying on fixed demographic categories. We demonstrate that recently introduced notions of multi-group fairness can be equivalently formulated as integral probability metrics (IPM). IPMs are the common information-theoretic tool that underlie definitions such as multiaccuracy, multicalibration, and outcome indistinguishably. For multiaccuracy, this connection leads to a simple, yet powerful procedure for achieving multiaccuracy with respect to an infinite-dimensional class of functions defined by a reproducing kernel Hilbert space (RKHS): first perform a kernel regression of a model’s errors, then subtract the resulting function from a model’s predictions. We combine these results to develop a post-processing method that improves multiaccuracy with respect to bounded-norm functions in an RKHS, enjoys provable performance guarantees, and, in binary classification benchmarks, achieves favorable multiaccuracy relative to competing methods.
more »
« less
- PAR ID:
- 10637900
- Editor(s):
- Bun, Mark
- Publisher / Repository:
- Schloss Dagstuhl – Leibniz-Zentrum für Informatik
- Date Published:
- Volume:
- 329
- ISSN:
- 1868-8969
- ISBN:
- 978-3-95977-367-6
- Page Range / eLocation ID:
- 7:1-7:23
- Subject(s) / Keyword(s):
- algorithmic fairness integral probability metrics information theory Mathematics of computing → Information theory
- Format(s):
- Medium: X Size: 23 pages; 10529789 bytes Other: application/pdf
- Size(s):
- 23 pages 10529789 bytes
- Right(s):
- Creative Commons Attribution 4.0 International license; info:eu-repo/semantics/openAccess
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
As learning-to-rank models are increasingly deployed for decision-making in areas with profound life implications, the FairML community has been developing fair learning-to-rank (LTR) models. These models rely on the availability of sensitive demographic features such as race or sex. However, in practice, regulatory obstacles and privacy concerns protect this data from collection and use. As a result, practitioners may either need to promote fairness despite the absence of these features or turn to demographic inference tools to attempt to infer them. Given that these tools are fallible, this paper aims to further understand how errors in demographic inference impact the fairness performance of popular fair LTR strategies. In which cases would it be better to keep such demographic attributes hidden from models versus infer them? We examine a spectrum of fair LTR strategies ranging from fair LTR with and without demographic features hidden versus inferred to fairness-unaware LTR followed by fair re-ranking. We conduct a controlled empirical investigation modeling different levels of inference errors by systematically perturbing the inferred sensitive attribute. We also perform three case studies with real-world datasets and popular open-source inference methods. Our findings reveal that as inference noise grows, LTR-based methods that incorporate fairness considerations into the learning process may increase bias. In contrast, fair re-ranking strategies are more robust to inference errors. All source code, data, and experimental artifacts of our experimental study are available here: https://github.com/sewen007/hoiltr.gitmore » « less
-
Abstract We develop a solvable model of neural scaling laws beyond the kernel limit. Theoretical analysis of this model shows how performance scales with model size, training time, and the total amount of available data. We identify three scaling regimes corresponding to varying task difficulties: hard, easy, and super easy tasks. For easy and super-easy target functions, which lie in the reproducing kernel Hilbert space (RKHS) defined by the initial infinite-width Neural Tangent Kernel (NTK), the scaling exponents remain unchanged between feature learning and kernel regime models. For hard tasks, defined as those outside the RKHS of the initial NTK, we demonstrate both analytically and empirically that feature learning can improve scaling with training time and compute, nearly doubling the exponent for hard tasks. This leads to a different compute optimal strategy to scale parameters and training time in the feature learning regime. We support our finding that feature learning improves the scaling law for hard tasks but not for easy and super-easy tasks with experiments of nonlinear MLPs fitting functions with power-law Fourier spectra on the circle and CNNs learning vision tasks.more » « less
-
Recent years have witnessed increasing concerns towards unfair decisions made by machine learning algorithms. To improve fairness in model decisions, various fairness notions have been proposed and many fairness-aware methods are developed. However, most of existing definitions and methods focus only on single-label classification. Fairness for multi-label classification, where each instance is associated with more than one labels, is still yet to establish. To fill this gap, we study fairness-aware multi-label classification in this paper. We start by extending Demographic Parity (DP) and Equalized Opportunity (EOp), two popular fairness notions, to multi-label classification scenarios. Through a systematic study, we show that on multi-label data, because of unevenly distributed labels, EOp usually fails to construct a reliable estimate on labels with few instances. We then propose a new framework named Similarity s-induced Fairness (sγ -SimFair). This new framework utilizes data that have similar labels when estimating fairness on a particular label group for better stability, and can unify DP and EOp. Theoretical analysis and experimental results on real-world datasets together demonstrate the advantage of sγ -SimFair over existing methods on multi-label classification tasks.more » « less
-
null (Ed.)Graph mining is an essential component of recommender systems and search engines. Outputs of graph mining models typically provide a ranked list sorted by each item's relevance or utility. However, recent research has identified issues of algorithmic bias in such models, and new graph mining algorithms have been proposed to correct for bias. As such, algorithm developers need tools that can help them uncover potential biases in their models while also exploring the impacts of correcting for biases when employing fairness-aware algorithms. In this paper, we present FairRankVis, a visual analytics framework designed to enable the exploration of multi-class bias in graph mining algorithms. We support both group and individual fairness levels of comparison. Our framework is designed to enable model developers to compare multi-class fairness between algorithms (for example, comparing PageRank with a debiased PageRank algorithm) to assess the impacts of algorithmic debiasing with respect to group and individual fairness. We demonstrate our framework through two usage scenarios inspecting algorithmic fairness.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.4230/LIPIcs.FORC.2025.7
