Invariant Representations through Adversarial Forgetting
Jaiswal, Ayush, Moyer, Daniel, Steeg, Greg Ver, AbdAlmageed, Wael, Natarajan, Premkumar
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.
Nov-20-2019
- Country:
- North America > United States
- California (0.14)
- Georgia > Fulton County
- Atlanta (0.04)
- Asia > Middle East
- Jordan (0.04)
- North America > United States
- Genre:
- Research Report > New Finding (0.34)
- Industry:
- Government (0.46)
- Technology: