Trustworthy Machine Learning under Distribution Shifts

TL;DR

This paper addresses the challenge of distribution shifts in machine learning, proposing solutions to improve robustness, explainability, and adaptability to enhance trustworthiness across various shift scenarios.

Contribution

It systematically studies three types of distribution shifts and investigates trustworthiness aspects, offering new insights and solutions for reliable ML under these conditions.

Findings

Analysis of perturbation, domain, and modality shifts.

Proposed methods to improve robustness and explainability.

Fundamental insights into trustworthiness under distribution shifts.

Abstract

Machine Learning (ML) has been a foundational topic in artificial intelligence (AI), providing both theoretical groundwork and practical tools for its exciting advancements. From ResNet for visual recognition to Transformer for vision-language alignment, the AI models have achieved superior capability to humans. Furthermore, the scaling law has enabled AI to initially develop general intelligence, as demonstrated by Large Language Models (LLMs). To this stage, AI has had an enormous influence on society and yet still keeps shaping the future for humanity. However, distribution shift remains a persistent ``Achilles' heel'', fundamentally limiting the reliability and general usefulness of ML systems. Moreover, generalization under distribution shift would also cause trust issues for AIs. Motivated by these challenges, my research focuses on \textit{Trustworthy Machine Learning under Distribution Shifts}, with the goal of expanding AI's robustness, versatility, as well as its responsibility and reliability. We carefully study the three common distribution shifts into: (1) Perturbation Shift, (2) Domain Shift, and (3) Modality Shift. For all scenarios, we also rigorously investigate trustworthiness via three aspects: (1) Robustness, (2) Explainability, and (3) Adaptability. Based on these dimensions, we propose effective solutions and fundamental insights, meanwhile aiming to enhance the critical ML problems, such as efficiency, adaptability, and safety.