Invariant Representations through Adversarial Forgetting

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 stateof-the-art performance at learning invariance in both nuisance and bias settings on a diverse collection of datasets and tasks.

Authors

• Ayush Jaiswal Amazon Alexa Natural Understanding
• Daniel Moyer
• Greg Ver Steeg
• Wael AbdAlmageed
• Premkumar Natarajan

Keywords

No keywords are indexed for this paper.