Learnable Graph Convolutional Network and Feature Fusion for Multi-view Learning
This work addresses a gap in multi-view learning for researchers and practitioners by enabling more effective integration of graph and feature information, though it is incremental as it builds on existing graph convolutional network methods.
The paper tackles the problem of learning discriminative node relationships and graph information simultaneously in multi-view data by proposing LGCN-FF, a joint deep learning framework that integrates feature fusion and learnable graph convolution, achieving superior performance in multi-view semi-supervised classification compared to state-of-the-art methods.
In practical applications, multi-view data depicting objectives from assorted perspectives can facilitate the accuracy increase of learning algorithms. However, given multi-view data, there is limited work for learning discriminative node relationships and graph information simultaneously via graph convolutional network that has drawn the attention from considerable researchers in recent years. Most of existing methods only consider the weighted sum of adjacency matrices, yet a joint neural network of both feature and graph fusion is still under-explored. To cope with these issues, this paper proposes a joint deep learning framework called Learnable Graph Convolutional Network and Feature Fusion (LGCN-FF), consisting of two stages: feature fusion network and learnable graph convolutional network. The former aims to learn an underlying feature representation from heterogeneous views, while the latter explores a more discriminative graph fusion via learnable weights and a parametric activation function dubbed Differentiable Shrinkage Activation (DSA) function. The proposed LGCN-FF is validated to be superior to various state-of-the-art methods in multi-view semi-supervised classification.