Deep Discrete Prototype Multilabel Learning

kNN embedding methods, such as the state-of-the-art LM-kNN, have shown impressive results in multi-label learning. Unfortunately, these approaches suffer expensive computation and memory costs in large-scale settings. To fill this gap, this paper proposes a novel deep prototype compression, i. e. , DBPC for fast multi-label prediction. DBPC compresses the database into a small set of short discrete prototypes, and uses the prototypes for prediction. The benefit of DBPC comes from two aspects: 1) The number of distance comparisons are reduced in the prototype; 2) The distance computation cost is significantly decreased in the reduced space. We propose to jointly learn the deep latent subspace and discrete prototypes within one framework. The encoding and decoding neural networks are employed to make deep discrete prototypes well represent the instances and labels. Extensive experiments on several large-scale datasets demonstrate that DBPC achieves several orders of magnitude lower storage and prediction complexity than state-of-the-art multi-label methods, while achieving competitive accuracy.

Authors

• Xiaobo Shen Nanjing University of Science and Technology
• Weiwei Liu Wuhan University
• Yong Luo
• Yew-Soon Ong Centre for Frontier AI Research, A*STAR & College of Computing and Data Science, NTU
• Ivor W. Tsang

Keywords

• Machine Learning: Classification
• Machine Learning: Multi-instance; Multi-label; Multi-view learning