Self-supervised Consensus Representation Learning for Attributed Graph

Abstract

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.

arXiv commentAccepted by ACM Multimedia 2021

References in corpus (20)

• Adam: A Method for Stochastic Optimization
• Distributed Representations of Words and Phrases and their Compositionality
• DeepWalk: Online Learning of Social Representations
• Semi-Supervised Classification with Graph Convolutional Networks
• A Simple Framework for Contrastive Learning of Visual Representations
• LINE: Large-scale Information Network Embedding
• Inductive Representation Learning on Large Graphs
• Spectral Networks and Locally Connected Networks on Graphs
• Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
• Cross-lingual Language Model Pretraining
• Simplifying Graph Convolutional Networks
• DeepInf: Social Influence Prediction with Deep Learning
• Deep Clustering for Unsupervised Learning of Visual Features
• Deep Graph Contrastive Representation Learning
• Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
• Robust Graph Learning from Noisy Data
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• Pseudo-supervised Deep Subspace Clustering
• Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach
• Towards Clustering-friendly Representations: Subspace Clustering via Graph Filtering

Cited by in corpus (4)

• Graph Self-Supervised Learning: A Survey
• Multi-View Subgraph Neural Networks: Self-Supervised Learning with Scarce Labeled Data
• Multi-view Contrastive Graph Clustering
• Select and Calibrate the Low-confidence: Dual-Channel Consistency based Graph Convolutional Networks