Hyperbolic Structured Classification for Robust Single Positive Multi-label Learning
This work addresses the challenge of incomplete supervision in multi-label classification for applications like image tagging, though it appears incremental by building on existing geometric methods.
The paper tackles the problem of Single Positive Multi-Label Learning (SPMLL), where training samples have only one positive label despite multiple categories, by proposing a hyperbolic classification framework that represents labels as hyperbolic balls to model inter-label relationships, achieving competitive performance on benchmark datasets like MS-COCO and PASCAL VOC with improved interpretability.
Single Positive Multi-Label Learning (SPMLL) addresses the challenging scenario where each training sample is annotated with only one positive label despite potentially belonging to multiple categories, making it difficult to capture complex label relationships and hierarchical structures. While existing methods implicitly model label relationships through distance-based similarity, lacking explicit geometric definitions for different relationship types. To address these limitations, we propose the first hyperbolic classification framework for SPMLL that represents each label as a hyperbolic ball rather than a point or vector, enabling rich inter-label relationship modeling through geometric ball interactions. Our ball-based approach naturally captures multiple relationship types simultaneously: inclusion for hierarchical structures, overlap for co-occurrence patterns, and separation for semantic independence. Further, we introduce two key component innovations: a temperature-adaptive hyperbolic ball classifier and a physics-inspired double-well regularization that guides balls toward meaningful configurations. To validate our approach, extensive experiments on four benchmark datasets (MS-COCO, PASCAL VOC, NUS-WIDE, CUB-200-2011) demonstrate competitive performance with superior interpretability compared to existing methods. Furthermore, statistical analysis reveals strong correlation between learned embeddings and real-world co-occurrence patterns, establishing hyperbolic geometry as a more robust paradigm for structured classification under incomplete supervision.