Self-supervised Consensus Representation Learning for Attributed Graph
arXiv:2108.04822 · doi:10.1145/3474085.3475416
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.
Accepted by ACM Multimedia 2021
References in corpus (9)
- Semi-Supervised Classification with Graph Convolutional Networks
- LINE: Large-scale Information Network Embedding
- Cross-lingual Language Model Pretraining
- Simplifying Graph Convolutional Networks
- 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
- Towards Clustering-friendly Representations: Subspace Clustering via Graph Filtering