Adaptation and Generalization for Unknown Sensitive Factors of Variations

TL;DR

This paper presents a framework for discovering and intervening on unknown sensitive factors affecting AI robustness, using unsupervised and semi-supervised methods to improve model performance across varying real-world conditions.

Contribution

The paper introduces a novel two-step approach combining unsupervised discovery of sensitive factors with intervention techniques, applicable in diverse settings with limited prior knowledge.

Findings

Interventions on discovered factors improve model robustness.

Semi-supervised adaptation enhances performance with partial label knowledge.

The approach outperforms baseline models in robustness and utility tradeoffs.

Abstract

Assured AI in unrestricted settings is a critical problem. Our framework addresses AI assurance challenges lying at the intersection of domain adaptation, fairness, and counterfactuals analysis, operating via the discovery and intervention on factors of variations in data (e.g. weather or illumination conditions) that significantly affect the robustness of AI models. Robustness is understood here as insensitivity of the model performance to variations in sensitive factors. Sensitive factors are traditionally set in a supervised setting, whereby factors are known a-priori (e.g. for fairness this could be factors like sex or race). In contrast, our motivation is real-life scenarios where less, or nothing, is actually known a-priori about certain factors that cause models to fail. This leads us to consider various settings (unsupervised, domain generalization, semi-supervised) that correspond to different degrees of incomplete knowledge about those factors. Therefore, our two step approach works by a) discovering sensitive factors that cause AI systems to fail in a unsupervised fashion, and then b) intervening models to lessen these factor's influence. Our method considers 3 interventions consisting of Augmentation, Coherence, and Adversarial Interventions (ACAI). We demonstrate the ability for interventions on discovered/source factors to generalize to target/real factors. We also demonstrate how adaptation to real factors of variations can be performed in the semi-supervised case where some target factor labels are known, via automated intervention selection. Experiments show that our approach improves on baseline models, with regard to achieving optimal utility vs. sensitivity/robustness tradeoffs.