Ran Gilad-Bachrach
Talk: Explainable AI: Theory and Algorithms
As Artificial Intelligence (AI) advances across domains, its inherent limitations and risks, such as bias, are becoming more apparent. To address these challenges, Explainable AI (xAI) has emerged as a key approach. This talk presents our efforts to build a theoretical foundation for xAI and develop algorithms to tackle its challenges.
We begin with a brief introduction to xAI, demonstrating its value through explainable algorithms for graph learning. We then take a theoretical view to establish a solid mathematical foundation for explainability. To do so, we focus on 'feature importance' as a method of explanation, particularly in the data-global setting. In this setting, a model serves as a proxy for understanding natural phenomena. Using an axiomatic approach, we show that a unique definition of feature importance arises in this context: the Marginal Contribution Feature Importance (MCI).
We then extend this definition beyond the data-global setting, highlighting inconsistencies in how explanations behave across different contexts. The talk concludes by examining the motivations behind seeking explanations, drawing parallels with the legal domain to understand the practice of reason-giving. This analysis assesses whether xAI meets these motivations—spoiler: it falls short.
BIO:
Ran Gilad-Bachrach, Ph.D., is an Associate Professor of Biomedical Engineering at Tel Aviv University, where he directs the MLwell Lab (Machine Learning for Health and Well-Being), applying machine learning to improve health, behavior change, and mental well-being.
He earned his doctorate at the Hebrew University of Jerusalem, founded a machine learning research group at Intel, and later joined Microsoft Research as both an applied and principal researcher.
His research develops algorithms and theory for machine learning in health and related domains, including privacy-preserving learning, optimization of behavioral interventions, and learning on graphs and sets.
He also heads the Digital Sciences for Hi-Tech program, leads the National Knowledge Center for AI Policy, and directs the Zimin Institute for Engineering Solutions Advancing Better Lives.