Multi-Context Label Embedding

Label embedding plays an important role in zero-shot learning. Side information such as attributes, semantic text representations, and label hierarchy are commonly used as the label embedding in zero-shot classification tasks. However, the label embedding used in former works considers either only one single context of the label, or multiple contexts without dependency. Therefore, different contexts of the label may not be well aligned in the embedding space to preserve the relatedness between labels, which will result in poor interpretability of the label embedding. In this paper, we propose a Multi-Context Label Embedding (MCLE) approach to incorporate multiple label contexts, e.g., label hierarchy and attributes, within a unified matrix factorization framework. To be specific, we model each single context by a matrix factorization formula and introduce a shared variable to capture the dependency among different contexts. Furthermore, we enforce sparsity constraint on our multi-context framework to strengthen the interpretability of the learned label embedding. Extensive experiments on two real-world datasets demonstrate the superiority of our MCLE in label description and zero-shot image classification.