Unified Risk Analysis for Weakly Supervised Learning
This work addresses a foundational problem for researchers in weakly supervised learning by offering a unified framework, though it appears incremental as it builds on and recovers existing methods.
The paper tackles the lack of a unified interpretation and systematic treatment of risk rewrite in weakly supervised learning by introducing a framework that provides a comprehensive understanding and methodology, recovering existing rewrites from the literature.
Among the flourishing research of weakly supervised learning (WSL), we recognize the lack of a unified interpretation of the mechanism behind the weakly supervised scenarios, let alone a systematic treatment of the risk rewrite problem, a crucial step in the empirical risk minimization approach. In this paper, we introduce a framework providing a comprehensive understanding and a unified methodology for WSL. The formulation component of the framework, leveraging a contamination perspective, provides a unified interpretation of how weak supervision is formed and subsumes fifteen existing WSL settings. The induced reduction graphs offer comprehensive connections over WSLs. The analysis component of the framework, viewed as a decontamination process, provides a systematic method of conducting risk rewrite. In addition to the conventional inverse matrix approach, we devise a novel strategy called marginal chain aiming to decontaminate distributions. We justify the feasibility of the proposed framework by recovering existing rewrites reported in the literature.