Log In Sign Up

Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning

by   Yizhu Jiao, et al.

Graph representation learning has attracted lots of attention recently. Existing graph neural networks fed with the complete graph data are not scalable due to limited computation and memory costs. Thus, it remains a great challenge to capture rich information in large-scale graph data. Besides, these methods mainly focus on supervised learning and highly depend on node label information, which is expensive to obtain in the real world. As to unsupervised network embedding approaches, they overemphasize node proximity instead, whose learned representations can hardly be used in downstream application tasks directly. In recent years, emerging self-supervised learning provides a potential solution to address the aforementioned problems. However, existing self-supervised works also operate on the complete graph data and are biased to fit either global or very local (1-hop neighborhood) graph structures in defining the mutual information based loss terms. In this paper, a novel self-supervised representation learning method via Subgraph Contrast, namely Subg-Con, is proposed by utilizing the strong correlation between central nodes and their sampled subgraphs to capture regional structure information. Instead of learning on the complete input graph data, with a novel data augmentation strategy, Subg-Con learns node representations through a contrastive loss defined based on subgraphs sampled from the original graph instead. Compared with existing graph representation learning approaches, Subg-Con has prominent performance advantages in weaker supervision requirements, model learning scalability, and parallelization. Extensive experiments verify both the effectiveness and the efficiency of our work compared with both classic and state-of-the-art graph representation learning approaches on multiple real-world large-scale benchmark datasets from different domains.


Self-Supervised Dynamic Graph Representation Learning via Temporal Subgraph Contrast

Self-supervised learning on graphs has recently drawn a lot of attention...

Unifying Graph Contrastive Learning with Flexible Contextual Scopes

Graph contrastive learning (GCL) has recently emerged as an effective le...

Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discrimination

Graph contrastive learning (GCL) alleviates the heavy reliance on label ...

Adversarial Representation Learning on Large-Scale Bipartite Graphs

Graph representation on large-scale bipartite graphs is central for a va...

Graph Representation Learning by Ensemble Aggregating Subgraphs via Mutual Information Maximization

Graph Neural Networks have shown tremendous potential on dealing with ga...

Generative Subgraph Contrast for Self-Supervised Graph Representation Learning

Contrastive learning has shown great promise in the field of graph repre...

SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanism

Graph representation learning has attracted increasing research attentio...

Code Repositories


Code for ICDM2020 full paper: "Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning"

view repo