Journal
IEEE TRANSACTIONS ON BIG DATA
Volume 8, Issue 5, Pages 1169-1181Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TBDATA.2020.3019478
Keywords
Correlation; Semantics; Social network services; Training; Task analysis; Proteins; Big Data; Multi-label graph; graph learning; network embedding; network representation learning; multi-label learning; neural networks
Funding
- U.S. National Science Foundation [IIS-1763452, CNS-1828181, OAC-2017597, IIS-2027339]
- Early-Career Research Fellowship from the Gulf Research Program (GRP) of the National Academies of Sciences, Engineering, and Medicine (NASEM)
Ask authors/readers for more resources
In this article, the authors propose a novel multi-label graph convolutional network (MuLGCN) for learning node representation in complex networks. They model a multi-label network as two Siamese GCNs and integrate them in one objective function to explore label-label correlation and network topology structures. Experiments validate the effectiveness of the proposed approach in multi-label node classification.
Knowledge representation of networked systems is fundamental in many disciplines. To date, existing methods for representation learning primarily focus on networks with simplex labels, yet real-world objects (nodes) are inherently complex in nature and often contain rich semantics or labels. For example, a user may belong to diverse interest groups of a social network, resulting in multi-label networks for many applications. A multi-label network not only has multiple labels for each node, the labels are often highly correlated making existing methods ineffective or even fail to handle such correlation for node representation learning. In this article, we propose a novel multi-label graph convolutional network (MuLGCN) for learning node representation. To fully explore label-label correlation and network topology structures, we propose to model a multi-label network as two Siamese GCNs: a node-node-label graph and a label-label-node graph. The two GCNs each handle one aspect of representation learning for nodes and labels, respectively, and are seamlessly integrated in one objective function. The learned label representations can effectively preserve the intra-label interaction and node label properties, and are aggregated to enhance the node representation learning under a unified training framework. Experiments and comparisons on multi-label node classification validate the effectiveness of our proposed approach.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available