Trustworthy Machine Learning under Distribution Shifts

Abstract

Machine Learning has been a foundational topic in artificial intelligence, 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. 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. As AI becomes increasingly integrated into real-world decision-making and societal infrastructures, the complexity of the practical problems continues to grow. These complex environments naturally introduce diverse and unpredictable distribution shifts, which can severely degrade model performance.

Moreover, generalization under distribution shift would also cause trust issues for AIs. For instance, when employing medical AIs across regions, they might perform unsatisfactorily and cause harm. Thus, we also consider the responsibility of AI, i.e., the Trustworthiness of ML, aiming to enhance reliability rather than merely focusing on accuracy.

Motivated by these challenges, my research focuses on Trustworthy Machine Learning under Distribution Shifts, with the goal of expanding AI's robustness, versatility, and 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, while aiming to enhance the critical ML problems, such as efficiency, adaptability, and safety.