DMRL-Net: Differentiable Multi-view Representation Learning Network

In recent years, deep multi-view representation learning has made considerable achievements due to its excellent nonlinear mapping capability. Yet its development is limited by the challenge of interpreting the underlying structure. For this reason, we propose a differentiable multi-view representation learning network to address the aforementioned issue, which is equipped with the interpretable working mechanism of sparse low-rank decomposition and outstanding representation ability of neural networks. The network is constructed by stacking multiple differentiable blocks that are explicitly reformulated from the optimization objective exhibiting interpretability. Benefiting from end-to-end optimization of deep networks, it can efficiently learn an interpretable deep representation of high-dimensional features from multi-view data. Extensive experimental results on several benchmark multi-view datasets demonstrate the effectiveness of the learned representation in comparison to several state-of-the-art algorithms.