Reliable Weakly Supervised Learning: Maximize Gain and Maintain Safeness

TL;DR

This paper introduces a novel weakly supervised learning framework that uses a small validation set to guide label quality optimization, ensuring safe performance improvements and avoiding degradation.

Contribution

It proposes a bi-level optimization approach that leverages validation data to enhance weakly supervised learning reliability and performance.

Findings

Achieves significant performance gains with minimal validation data

Effectively prevents performance degradation due to label noise

Outperforms existing methods on benchmark datasets

Abstract

Weakly supervised data are widespread and have attracted much attention. However, since label quality is often difficult to guarantee, sometimes the use of weakly supervised data will lead to unsatisfactory performance, i.e., performance degradation or poor performance gains. Moreover, it is usually not feasible to manually increase the label quality, which results in weakly supervised learning being somewhat difficult to rely on. In view of this crucial issue, this paper proposes a simple and novel weakly supervised learning framework. We guide the optimization of label quality through a small amount of validation data, and to ensure the safeness of performance while maximizing performance gain. As validation set is a good approximation for describing generalization risk, it can effectively avoid the unsatisfactory performance caused by incorrect data distribution assumptions. We formalize this underlying consideration into a novel Bi-Level optimization and give an effective solution. Extensive experimental results verify that the new framework achieves impressive performance on weakly supervised learning with a small amount of validation data.