Towards Algorithmic Fairness by means of Instance-level Data Re-weighting based on Shapley Values

ICLR 2024 Workshop DMLR Submission36 Authors

Published: 04 Mar 2024, Last Modified: 02 May 2024DMLR @ ICLR 2024EveryoneRevisionsBibTeXCC BY 4.0
Keywords: Algorithmic Fairness, Data Valuation, Shapley Values, Re-weighting
TL;DR: FairShap is a novel method for fair algorithmic decision-making by re-weighting data, focusing on fair data valuation using Shapley Values.
Abstract:

Algorithmic fairness is of utmost societal importance, yet state-of-the-art large-scale machine learning models require training with massive datasets that are frequently biased. In this context, pre-processing methods that focus on modeling and correcting bias in the data emerge as valuable approaches. In this paper, we propose FairShap, a novel instance-level data re-weighting method for fair algorithmic decision-making through data valuation by means of Shapley Values. FairShap is model-agnostic and easily interpretable. It measures the contribution of each training data point to a predefined fairness metric. We empirically validate FairShap on several state-of-the-art datasets of different nature, with a variety of training scenarios and machine learning models and show how it yields fairer models with similar levels of accuracy than the baselines. We illustrate FairShap's interpretability by means of histograms and latent space visualizations and perform a utility-fairness study. We believe that FairShap represents a promising direction in interpretable and model-agnostic approaches to algorithmic fairness that yield competitive accuracy even when only biased datasets are available.

Primary Subject Area: Other
Paper Type: Research paper: up to 8 pages
DMLR For Good Track: Participate in DMLR for Good Track
Participation Mode: In-person
Confirmation: I have read and agree with the workshop's policy on behalf of myself and my co-authors.
Submission Number: 36
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview