Prototypical Networks for Multi-Label Learning
This addresses multi-label classification, a common problem in machine learning for tasks like image tagging, but it appears incremental as it builds on existing embedding and prototype-based methods.
The paper tackles multi-label learning by modeling class distributions in a shared embedding space, where positive and negative components for each label are compact and separated, and it achieves more accurate classification than state-of-the-art algorithms in experiments.
We propose to formulate multi-label learning as a estimation of class distribution in a non-linear embedding space, where for each label, its positive data embeddings and negative data embeddings distribute compactly to form a positive component and negative component respectively, while the positive component and negative component are pushed away from each other. Duo to the shared embedding space for all labels, the distribution of embeddings preserves instances' label membership and feature matrix, thus encodes the feature-label relation and nonlinear label dependency. Labels of a given instance are inferred in the embedding space by measuring the probabilities of its belongingness to the positive or negative components of each label. Specially, the probabilities are modeled as the distance from the given instance to representative positive or negative prototypes. Extensive experiments validate that the proposed solution can provide distinctively more accurate multi-label classification than other state-of-the-art algorithms.