Learning fair representations via an adversarial framework

Rui Feng · Ruoyun Hu · Shaowa Lin · Quanjin Tao

42 citations0/0 files storedAI Open

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

Fairness has become a central issue for our research community as classification algorithms are adopted in societally critical domains such as recidivism prediction and loan approval. In this work, we consider the potential bias based on protected attributes (e.g., race and gender), and tackle this problem by learning latent representations of individuals that are statistically indistinguishable between protected groups while sufficiently preserving other information for classification.To do that, we develop a minimax adversarial framework with a generator to capture the data distribution and generate latent representations, and a critic to ensure that the distributions across different protected groups are similar. Our framework provides theoretical guarantee with respect statistical parity and individual fairness. Empirical results on four real-world datasets also show that the learned representation can effectively be used for classification tasks such as credit risk prediction while obstructing information related to protected groups, especially when removing protected attributes is not sufficient for fair classification.

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 — 42 citations exist upstream.

References

2012Fairness through awareness 2016Equality of Opportunity in Supervised Learning 2017Fair Prediction with Disparate Impact: A Study of Bias in Recidivism Prediction Instruments 2015Certifying and Removing Disparate Impact 2018Mitigating Unwanted Biases with Adversarial Learning 2011Data preprocessing techniques for classification without discrimination 2017Algorithmic Decision Making and the Cost of Fairness 2013Learning Fair Representations

Cited by

2021Fairness in Semi-supervised Learning: Unlabeled Data Help to Reduce Discrimination 2021Socially Responsible AI Algorithms: Issues, Purposes, and Challenges 2025Towards Fair AI: Mitigating Bias in Credit Decisions—A Systematic Literature Review 2022An information theoretic approach to reducing algorithmic bias for machine learning 2021FAWOS: Fairness-Aware Oversampling Algorithm Based on Distributions of Sensitive Attributes 2022On the fairness of generative adversarial networks (GANs)

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.