Multiview Graph Convolutional Network Research Articles

Semi-supervised multi-view graph convolutional networks with application to webpage classification

Semi-supervised multi-view learning (SML) is a hot research topic in recent years, with webpage classification being a typical application domain. The performance of SML is further boosted by the successful introduction of graph convolutional network (GCN) for learning discriminant node representations. However, there remains much space to improve the GCN-based SML technique, particularly on how to adaptively learn optimal graph structures for multi-view graph convolutional representation learning and make full use of the label and structure information in labeled and unlabeled multi-view samples. In this paper, we propose a novel SML approach named semi-supervised multi-view graph convolutional networks (SMGCN) for webpage classification. It contains a multi-view graph construction module and a semi-supervised multi-view graph convolutional representation learning module, which are integrated into a unified network architecture. The former aims to obtain optimal graph structure for each view. And the latter performs graph convolutional representation learning for each view, and provides an inter-view attention scheme to fuse multi-view representations. Network training is guided by the losses defined on both label and feature spaces, such that the label and structure information in labeled and unlabeled data is fully explored. Experiments on two widely used webpage datasets demonstrate that SMGCN can achieve state-of-the-art classification performance.

MVGCN: data integration through multi-view graph convolutional network for predicting links in biomedical bipartite networks.

There are various interaction/association bipartite networks in biomolecular systems. Identifying unobserved links in biomedical bipartite networks helps to understand the underlying molecular mechanisms of human complex diseases and thus benefits the diagnosis and treatment of diseases. Although a great number of computational methods have been proposed to predict links in biomedical bipartite networks, most of them heavily depend on features and structures involving the bioentities in one specific bipartite network, which limits the generalization capacity of applying the models to other bipartite networks. Meanwhile, bioentities usually have multiple features, and how to leverage them has also been challenging. In this study, we propose a novel multi-view graph convolution network (MVGCN) framework for link prediction in biomedical bipartite networks. We first construct a multi-view heterogeneous network (MVHN) by combining the similarity networks with the biomedical bipartite network, and then perform a self-supervised learning strategy on the bipartite network to obtain node attributes as initial embeddings. Further, a neighborhood information aggregation (NIA) layer is designed for iteratively updating the embeddings of nodes by aggregating information from inter- and intra-domain neighbors in every view of the MVHN. Next, we combine embeddings of multiple NIA layers in each view, and integrate multiple views to obtain the final node embeddings, which are then fed into a discriminator to predict the existence of links. Extensive experiments show MVGCN performs better than or on par with baseline methods and has the generalization capacity on six benchmark datasets involving three typical tasks. Source code and data can be downloaded from https://github.com/fuhaitao95/MVGCN. Supplementary data are available at Bioinformatics online.

Multitask Representation Learning With Multiview Graph Convolutional Networks.

Link prediction and node classification are two important downstream tasks of network representation learning. Existing methods have achieved acceptable results but they perform these two tasks separately, which requires a lot of duplication of work and ignores the correlations between tasks. Besides, conventional models suffer from the identical treatment of information of multiple views, thus they fail to learn robust representation for downstream tasks. To this end, we tackle link prediction and node classification problems simultaneously via multitask multiview learning in this article. We first explain the feasibility and advantages of multitask multiview learning for these two tasks. Then we propose a novel model named MT-MVGCN to perform link prediction and node classification tasks simultaneously. More specifically, we design a multiview graph convolutional network to extract abundant information of multiple views in a network, which is shared by different tasks. We further apply two attention mechanisms: view the attention mechanism and task attention mechanism to make views and tasks adjust the view fusion process. Moreover, view reconstruction can be introduced as an auxiliary task to boost the performance of the proposed model. Experiments on real-world network data sets demonstrate that our model is efficient yet effective, and outperforms advanced baselines in these two tasks.

Adaptive multi-view graph convolutional networks for skeleton-based action recognition

Skeleton based human action recognition has attracted more and more attentions recently thanks to the accessibility of depth sensors and the development of pose estimation techniques. Conventional approaches such as convolutional neural networks usually model skeletons with grid-shaped representations, which cannot explicitly explore the dependency between two correlated joints. In this paper, we treat the skeleton as a single graph with joints as nodes and bones as edges. Based on the skeleton graph, the improved graph convolutional network called adaptive multi-view graph convolutional networks(AMV-GCNs) is proposed to deal with skeleton based action recognition. We firstly construct a novel skeleton graph and two kinds of graph nodes are defined to model the spatial configuration and temporal dynamics respectively. Then the generated graphs along with feature vectors on graph nodes are fed into AMV-GCNs. In AMV-GCNs, an adaptive view transformation module is designed to reduce the impact of view diversity. Proposed module can automatically determine suitable viewpoints and transform skeletons to new representations under those viewpoints for better recognition. Further, we employ multiple GCNs based streams to utilize and learn action information from different viewpoints. Finally, the classification scores from multiple streams are fused to provide the recognition result. Extensive experimental evaluations on four challenging datasets, NTU RGB+D 60, NTU RGB+D 120, Northwestern-UCLA and UTD-MHAD, demonstrate the superiority of our proposed network.