Can Class-Priors Help Single-Positive Multi-Label Learning?

TL;DR

This paper introduces a novel framework that estimates class priors in single-positive multi-label learning, improving model performance by addressing prior probability assumptions and demonstrating effectiveness on multiple datasets.

Contribution

The paper proposes a class-priors estimator and an unbiased risk estimator for SPMLL, which together improve learning accuracy by accounting for class prior differences.

Findings

The method accurately estimates class priors that converge to true values.

The risk estimator leads to models approaching fully supervised performance.

Experimental results show superior performance over existing SPMLL methods.

Abstract

Single-positive multi-label learning (SPMLL) is a typical weakly supervised multi-label learning problem, where each training example is annotated with only one positive label. Existing SPMLL methods typically assign pseudo-labels to unannotated labels with the assumption that prior probabilities of all classes are identical. However, the class-prior of each category may differ significantly in real-world scenarios, which makes the predictive model not perform as well as expected due to the unrealistic assumption on real-world application. To alleviate this issue, a novel framework named {\proposed}, i.e., Class-pRiors Induced Single-Positive multi-label learning, is proposed. Specifically, a class-priors estimator is introduced, which could estimate the class-priors that are theoretically guaranteed to converge to the ground-truth class-priors. In addition, based on the estimated class-priors, an unbiased risk estimator for classification is derived, and the corresponding risk minimizer could be guaranteed to approximately converge to the optimal risk minimizer on fully supervised data. Experimental results on ten MLL benchmark datasets demonstrate the effectiveness and superiority of our method over existing SPMLL approaches.