RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Rank Correlation between Labels

Pseudo label based semi-supervised learning (SSL) for single-label and multilabel classification tasks has been extensively studied; however, semi-supervised label distribution learning (SSLDL) remains a largely unexplored area. Existing SSL methods fail in SSLDL because the pseudo-labels they generate only ensure overall similarity to the ground truth but do not preserve the ranking relationships between true labels, as they rely solely on KL divergence as the loss function during training. These skewed pseudo-labels lead the model to learn incorrect semantic relationships, resulting in reduced performance accuracy. To address these issues, we propose a novel SSLDL method called RankMatch. RankMatch fully considers the ranking relationships between different labels during the training phase with labeled data to generate higher-quality pseudo-labels. Furthermore, our key observation is that a flexible utilization of pseudo-labels can enhance SSLDL performance. Specifically, focusing solely on the ranking relationships between labels while disregarding their margins helps prevent model overfitting. Theoretically, we prove that incorporating ranking correlations enhances SSLDL performance and establish generalization error bounds for RankMatch. Finally, extensive real-world experiments validate its effectiveness. * Corresponding authors. 2 LDL is similar to learning from soft labels, but the soft-label formulation focuses on single-label problems (i.e., there is only one true label for each instance), while LDL considers multi-label problems (i.e., each instance can have multiple true labels). 39th Conference on Neural Information Processing Systems (NeurIPS 2025).