Robustness and Adaptation to Hidden Factors of Variation
This work tackles robustness to hidden factors for AI models, but it appears incremental as it builds on existing concepts of invariance and interventions.
The paper addresses the problem of making AI models robust to hidden factors of variation by using a two-step strategy involving unsupervised discovery of sensitive factors and interventions like data augmentation to achieve invariance, showing benefits in unsupervised, semi-supervised, and generalization settings.
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).