Active Refinement for Multi-Label Learning: A Pseudo-Label Approach

TL;DR

This paper introduces an active refinement method for multi-label learning that uses pseudo-labels to improve classification of fine-grained concepts and strategically query annotations, especially when initial data is limited.

Contribution

It formalizes a weakly supervised multi-label learning framework with pseudo-labeling and active querying, enabling efficient refinement of concepts with minimal labeled data.

Findings

Significantly improves multi-label classification accuracy.

Effectively recovers missing ground truth labels.

Enhances active learning strategies for concept refinement.

Abstract

The goal of multi-label learning (MLL) is to associate a given instance with its relevant labels from a set of concepts. Previous works of MLL mainly focused on the setting where the concept set is assumed to be fixed, while many real-world applications require introducing new concepts into the set to meet new demands. One common need is to refine the original coarse concepts and split them into finer-grained ones, where the refinement process typically begins with limited labeled data for the finer-grained concepts. To address the need, we formalize the problem into a special weakly supervised MLL problem to not only learn the fine-grained concepts efficiently but also allow interactive queries to strategically collect more informative annotations to further improve the classifier. The key idea within our approach is to learn to assign pseudo-labels to the unlabeled entries, and in turn leverage the pseudo-labels to train the underlying classifier and to inform a better query strategy. Experimental results demonstrate that our pseudo-label approach is able to accurately recover the missing ground truth, boosting the prediction performance significantly over the baseline methods and facilitating a competitive active learning strategy.