A Pseudo-Label Method for Coarse-to-Fine Multi-Label Learning with Limited Supervision
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 propose a special weakly supervised MLL problem that not only focuses on the situation of limited fine-grained supervision but also leverages the hierarchical relationship between the coarse concepts and the fine-grained ones. The problem can be reduced to a multi-label version of negative-unlabeled learning problem using the hierarchical relationship. We tackle the reduced problem with a meta-learning approach that learns to assign pseudo-labels to the unlabeled entries. Experimental results demonstrate that our proposed method is able to assign accurate pseudo-labels, and in turn achieves superior classification performance when compared with other existing methods.
PDF Abstract