Progressive Deep Multi-View Comprehensive Representation Learning

Multi-view Comprehensive Representation Learning (MCRL) aims to synthesize information from multiple views learn comprehensive representations of data items. Prevalent deep MCRL methods typically concatenate synergistic view-specific or average aligned in the fusion stage. However, performance inevitably degenerate even fail when partial are missing real-world applications; based usually cannot fully exploit complementarity multi-view data. To eliminate all these drawbacks, this work we present a Progressive Deep Fusion (PDMF) method. Considering representation should contain complete and information, deem that it is unstable directly mapping information. Hence, PDMF employs progressive learning strategy, which contains pre-training fine-tuning stages. In stage, decodes auxiliary It also captures consistency by relations between dimensions views. learns original with help relations. Experiments conducted on synthetic toy dataset 4 datasets show outperforms state-of-the-art baseline methods. The code released at https://github.com/winterant/PDMF.