Self-supervised Consensus Representation Learning for Attributed Graph
This work addresses the challenge of effectively utilizing both structure and features in graph representation learning for domains like social networks, though it is incremental as it builds on existing graph convolutional networks and self-supervised methods.
The authors tackled the problem of learning representations for attributed graphs by proposing a self-supervised framework that leverages both topological and feature graphs to maximize agreement between embeddings, achieving state-of-the-art results on semi-supervised node classification tasks in citation and social networks.
Attempting to fully exploit the rich information of topological structure and node features for attributed graph, we introduce self-supervised learning mechanism to graph representation learning and propose a novel Self-supervised Consensus Representation Learning (SCRL) framework. In contrast to most existing works that only explore one graph, our proposed SCRL method treats graph from two perspectives: topology graph and feature graph. We argue that their embeddings should share some common information, which could serve as a supervisory signal. Specifically, we construct the feature graph of node features via k-nearest neighbor algorithm. Then graph convolutional network (GCN) encoders extract features from two graphs respectively. Self-supervised loss is designed to maximize the agreement of the embeddings of the same node in the topology graph and the feature graph. Extensive experiments on real citation networks and social networks demonstrate the superiority of our proposed SCRL over the state-of-the-art methods on semi-supervised node classification task. Meanwhile, compared with its main competitors, SCRL is rather efficient.