Similarity-based Multi-label Learning
This work addresses multi-label learning, a common problem in applications like text categorization and image tagging, but appears incremental as it builds on existing similarity-based methods.
The authors tackled multi-label classification by proposing a similarity-based approach called SML, which includes predicting label set size and shows favorable performance compared to existing algorithms across various evaluation criteria.
Multi-label classification is an important learning problem with many applications. In this work, we propose a principled similarity-based approach for multi-label learning called SML. We also introduce a similarity-based approach for predicting the label set size. The experimental results demonstrate the effectiveness of SML for multi-label classification where it is shown to compare favorably with a wide variety of existing algorithms across a range of evaluation criterion.