Generative Fairness Teaching

Rongmei Lin, Hanjun Dai, Li Xiong, Wei Wei

Keywords: fairness, student teacher model, counterfactual generative model

Abstract: Increasing evidences has shown that data biases towards sensitive features such as gender or race are often inherited or even amplified by machine learning models. Recent advancements in fairness mitigate such biases by adjusting the predictions across sensitive groups during the training. Such a correction, however, can only take advantage of samples in a fixed dataset, which usually has limited amount of samples for the minority groups. We propose a generative fairness teaching framework that provides a model with not only real samples but also synthesized samples to compensate the data biases during training. We employ such a teaching strategy by implementing a Generative Fairness Teacher (GFT) that dynamically adjust the proportion of training data for a biased student model. Experimental results indicated that our teacher model is capable of guiding a wide range of biased models by improving the fairness and performance trade-offs significantly.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: Teaching machines to achieve fairness by using a counterfactual generative model

Reviewed Version (pdf): https://openreview.net/references/pdf?id=eTXTcj8Npb