Reliable Weakly Supervised Learning: Maximize Gain and Maintain Safeness
This addresses the challenge of making weakly supervised learning more reliable for practitioners dealing with noisy or incomplete labels, though it is incremental in improving existing methods.
The paper tackles the problem of unreliable performance in weakly supervised learning due to poor label quality by proposing a framework that uses a small validation set to optimize label quality and ensure safeness while maximizing gain, achieving impressive performance.
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.