Timezone: »

Invariant Representations without Adversarial Training
Daniel Moyer · Shuyang Gao · Rob Brekelmans · Aram Galstyan · Greg Ver Steeg

Thu Dec 06 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #120

Representations of data that are invariant to changes in specified factors are useful for a wide range of problems: removing potential biases in prediction problems, controlling the effects of covariates, and disentangling meaningful factors of variation. Unfortunately, learning representations that exhibit invariance to arbitrary nuisance factors yet remain useful for other tasks is challenging. Existing approaches cast the trade-off between task performance and invariance in an adversarial way, using an iterative minimax optimization. We show that adversarial training is unnecessary and sometimes counter-productive; we instead cast invariant representation learning as a single information-theoretic objective that can be directly optimized. We demonstrate that this approach matches or exceeds performance of state-of-the-art adversarial approaches for learning fair representations and for generative modeling with controllable transformations.

Author Information

Daniel Moyer (University of Southern California)
Shuyang Gao (ISI USC)
Rob Brekelmans (University of Southern California)
Aram Galstyan (USC Information Sciences Inst)
Greg Ver Steeg (University of Southern California)

More from the Same Authors