Self-attention Multi-view Representation Learning with Diversity-promoting Complementarity
This work addresses multi-view learning for researchers, offering an incremental improvement by focusing on diverse complementarity rather than single complementarity.
The paper tackles the problem of multi-view representation learning by proposing a method that exploits both consistency and diversity-promoting complementarity, achieving superior performance over baselines on eight real-world datasets.
Multi-view learning attempts to generate a model with a better performance by exploiting the consensus and/or complementarity among multi-view data. However, in terms of complementarity, most existing approaches only can find representations with single complementarity rather than complementary information with diversity. In this paper, to utilize both complementarity and consistency simultaneously, give free rein to the potential of deep learning in grasping diversity-promoting complementarity for multi-view representation learning, we propose a novel supervised multi-view representation learning algorithm, called Self-Attention Multi-View network with Diversity-Promoting Complementarity (SAMVDPC), which exploits the consistency by a group of encoders, uses self-attention to find complementary information entailing diversity. Extensive experiments conducted on eight real-world datasets have demonstrated the effectiveness of our proposed method, and show its superiority over several baseline methods, which only consider single complementary information.