🤖 AI Summary
Existing multi-view multi-label classification methods suffer from two critical limitations: (1) blind separation of “negative pairs” in multi-view contrastive learning, which disrupts semantic consistency among same- or similar-class samples; and (2) neglect of the prevalent real-world scenario involving both incomplete views and missing labels. To address these challenges, we propose RANK—the first robust classification framework explicitly designed for incomplete multi-view and partially observed multi-label data. Its key innovations include: (1) a label-guided contrastive learning mechanism that preserves categorical semantic structure; (2) a quality-aware subnetwork that dynamically evaluates and weights view reliability; and (3) explicit modeling of label correlations within the classification loss. Extensive experiments demonstrate that RANK consistently outperforms state-of-the-art methods on both complete and incomplete datasets, achieving significant gains in classification accuracy and robustness to label and view incompleteness.
📝 Abstract
As a cross-topic of multi-view learning and multi-label classification, multi-view multi-label classification has gradually gained traction in recent years. The application of multi-view contrastive learning has further facilitated this process; however, the existing multi-view contrastive learning methods crudely separate the so-called negative pair, which largely results in the separation of samples belonging to the same category or similar ones. Besides, plenty of multi-view multi-label learning methods ignore the possible absence of views and labels. To address these issues, in this paper, we propose an incomplete multi-view missing multi-label classification network named RANK. In this network, a label-driven multi-view contrastive learning strategy is proposed to leverage supervised information to preserve the intra-view structure and perform the cross-view consistency alignment. Furthermore, we break through the view-level weights inherent in existing methods and propose a quality-aware subnetwork to dynamically assign quality scores to each view of each sample. The label correlation information is fully utilized in the final multi-label cross-entropy classification loss, effectively improving the discriminative power. Last but not least, our model is not only able to handle complete multi-view multi-label data, but also works on datasets with missing instances and labels. Extensive experiments confirm that our RANK outperforms existing state-of-the-art methods.
