Poster

FR-Train: A Mutual Information-Based Approach to Fair and Robust Training

Yuji Roh · Kangwook Lee · Steven Whang · Changho Suh

Keywords: [ Crowdsourcing ] [ Generative Adversarial Networks ] [ Robust Statistics and Machine Learning ] [ Fairness, Equity and Justice ] [ Fairness, Equity, Justice, and Safety ]

[ Abstract ] [ Join Zoom
[ Slides
Please do not share or post zoom links

Abstract:

Trustworthy AI is a critical issue in machine learning where, in addition to training a model that is accurate, one must consider both fair and robust training in the presence of data bias and poisoning. However, the existing model fairness techniques mistakenly view poisoned data as an additional bias to be fixed, resulting in severe performance degradation. To address this problem, we propose FR-Train, which holistically performs fair and robust model training. We provide a mutual information-based interpretation of an existing adversarial training-based fairness-only method, and apply this idea to architect an additional discriminator that can identify poisoned data using a clean validation set and reduce its influence. In our experiments, FR-Train shows almost no decrease in fairness and accuracy in the presence of data poisoning by both mitigating the bias and defending against poisoning. We also demonstrate how to construct clean validation sets using crowdsourcing, and release new benchmark datasets.

Chat is not available.