Fair Mixup: Fairness via Interpolation

Ching-Yao Chuang · Youssef Mroueh

65 citations0/0 files storedarXiv (Cornell University)

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Ethics and Social Impacts of AI Privacy-Preserving Technologies in Data Explainable Artificial Intelligence (XAI)

Abstract

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.

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 65 citations exist upstream.

References

2012Fairness through awareness 2016Equality of Opportunity in Supervised Learning 2018Mitigating Unwanted Biases with Adversarial Learning 2013Learning Fair Representations 2018Fairness in Criminal Justice Risk Assessments: The State of the Art 2015Fairness Constraints: Mechanisms for Fair Classification 2018Learning Adversarially Fair and Transferable Representations

Cited by

2022Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers 2023Multi-task learning with dynamic re-weighting to achieve fairness in healthcare predictive modeling 2022Learning Fair Classifiers with Partially Annotated Group Labels 2022Improving fairness generalization through a sample-robust optimization method 2023Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools 2022Why Knowledge Distillation Amplifies Gender Bias and How to Mitigate from the Perspective of DistilBERT

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.