Unified Risk Analysis for Weakly Supervised Learning

by   Chao-Kai Chiang, et al.

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.


page 1

page 2

page 3

page 4


Audio Event and Scene Recognition: A Unified Approach using Strongly and Weakly Labeled Data

In this paper we propose a novel learning framework called Supervised an...

Onion Universe Algorithm: Applications in Weakly Supervised Learning

We introduce Onion Universe Algorithm (OUA), a novel classification meth...

Cross-task weakly supervised learning from instructional videos

In this paper we investigate learning visual models for the steps of ord...

From Weakly Supervised Learning to Biquality Learning, a brief introduction

The field of Weakly Supervised Learning (WSL) has recently seen a surge ...

Decoupling Makes Weakly Supervised Local Feature Better

Weakly supervised learning can help local feature methods to overcome th...

Learning by Fixing: Solving Math Word Problems with Weak Supervision

Previous neural solvers of math word problems (MWPs) are learned with fu...

Please sign up or login with your details

Forgot password? Click here to reset