ESA: Example Sieve Approach for Multi-Positive and Unlabeled Learning
This work addresses a practical challenge in MPU learning, which is important for applications dealing with partially labeled data, but it appears incremental as it builds on existing risk estimation methods.
The paper tackles the problem of learning from Multi-Positive and Unlabeled (MPU) data, where models suffer from a shift in minimum risk, and proposes an Example Sieve Approach (ESA) that selects examples using Certain Loss values to train a multi-class classifier, achieving optimal parametric convergence rates and outperforming previous methods in experiments on real-world datasets.
Learning from Multi-Positive and Unlabeled (MPU) data has gradually attracted significant attention from practical applications. Unfortunately, the risk of MPU also suffer from the shift of minimum risk, particularly when the models are very flexible as shown in Fig.\ref{moti}. In this paper, to alleviate the shifting of minimum risk problem, we propose an Example Sieve Approach (ESA) to select examples for training a multi-class classifier. Specifically, we sieve out some examples by utilizing the Certain Loss (CL) value of each example in the training stage and analyze the consistency of the proposed risk estimator. Besides, we show that the estimation error of proposed ESA obtains the optimal parametric convergence rate. Extensive experiments on various real-world datasets show the proposed approach outperforms previous methods.