[3A1] [General Session] 2. Machine Learning

[3A1-05] Similarity Learning Based Adversarial Training for Censoring Representatoins

〇Yusuke Iwasawa¹, Yutaka Matsuo¹ (1. The University of Tokyo)

Keywords:Adversarial training, Deep Learning, Fairness/Privacy

Deep neural networks (DNN) continuously demonstrates excellent performance in various application domains. However, how to control the representations is critical issues to use DNN in real-world scenarios. Notably, control the invariance of the representations is essential to incorporate social constraints, such as privacy-protection and fairness. This paper proposes a novel way to control the representations learned by DNN, called similarity confusion training. Empirical validations on a task of learning anonymous representations from the data of wearables show that the proposed method successfully remove unwanted information with less performance degradation compared to the existing methods.