Partial Label Learning via Mutual Information Representation Learning

Partial label learning (PLL) is a paradigm in weakly supervised learning. The goal is to identify the ground-truth label from a set of candidate labels associated with a given sample. However, due to the ambiguity of labels, improving the accuracy of ground-truth label recognition is a challenge. In this paper, we propose an innovative training framework PLMR, for solving the PLL problem. Given the specificity of the PLL problem, its data is rich in valid information but significantly noisy. To overcome the problem, PLMR incorporates mutual information (MI) theory to mine the potential information of candidate labels and data features to distinguish between positive and negative sample pairs. This operation is to effectively utilize the raw data information in PLL and reduce the class conflict problem. In this way, the discriminative power of representation is improved according to the positive and negative pair selection strategy. At the same time, PLMR introduces cluster centers to optimize subsequent tasks, combining data augmentation samples with the K-means cross-attention mechanism to refine the optimized cluster centers. This is to improve the ability of the clustering centre to accurately represent the class information, thus improving the overall quality of the clusters. Further, through the ambiguity marking correction mechanism, weights are calculated based on the association between cluster centers and sample representations to guide model training. Experimental results show that PLMR demonstrates excellent classification performance on multiple datasets, verifying its effectiveness and sophistication.