Invariant Representations through Adversarial Forgetting

  • Ayush Jaiswal USC Information Sciences Institute
  • Daniel Moyer USC Information Sciences Institute
  • Greg Ver Steeg USC Information Sciences Institute
  • Wael AbdAlmageed USC Information Sciences Institute
  • Premkumar Natarajan USC Information Sciences Institute

Abstract

We propose a novel approach to achieving invariance for deep neural networks in the form of inducing amnesia to unwanted factors of data through a new adversarial forgetting mechanism. We show that the forgetting mechanism serves as an information-bottleneck, which is manipulated by the adversarial training to learn invariance to unwanted factors. Empirical results show that the proposed framework achieves state-of-the-art performance at learning invariance in both nuisance and bias settings on a diverse collection of datasets and tasks.

Published
2020-04-03
Section
AAAI Technical Track: Machine Learning