Unified Risk Analysis for Weakly Supervised Learning

Understand

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.