Robustness and Adaptation to Hidden Factors of Variation

TL;DR

This paper proposes a two-step method to improve AI robustness by discovering hidden variation factors with generative models and intervening to make models invariant to these factors, enhancing performance across various settings.

Contribution

It introduces a novel approach combining unsupervised discovery and intervention techniques to achieve invariance to hidden data variations, addressing a less-explored aspect of robustness.

Findings

Improved invariance without significant utility loss

Effective across unsupervised, semi-supervised, and generalization scenarios

Demonstrated benefits of multiple intervention strategies

Abstract

We tackle here a specific, still not widely addressed aspect, of AI robustness, which consists of seeking invariance / insensitivity of model performance to hidden factors of variations in the data. Towards this end, we employ a two step strategy that a) does unsupervised discovery, via generative models, of sensitive factors that cause models to under-perform, and b) intervenes models to make their performance invariant to these sensitive factors' influence. We consider 3 separate interventions for robustness, including: data augmentation, semantic consistency, and adversarial alignment. We evaluate our method using metrics that measure trade offs between invariance (insensitivity) and overall performance (utility) and show the benefits of our method for 3 settings (unsupervised, semi-supervised and generalization).