Graph Communal Contrastive Learning

Abstract

Graph representation learning is crucial for many real-world applications (e.g. social relation analysis). A fundamental problem for graph representation learning is how to effectively learn representations without human labeling, which is usually costly and time-consuming. Graph contrastive learning (GCL) addresses this problem by pulling the positive node pairs (or similar nodes) closer while pushing the negative node pairs (or dissimilar nodes) apart in the representation space. Despite the success of the existing GCL methods, they primarily sample node pairs based on the node-level proximity yet the community structures have rarely been taken into consideration. As a result, two nodes from the same community might be sampled as a negative pair. We argue that the community information should be considered to identify node pairs in the same communities, where the nodes insides are semantically similar. To address this issue, we propose a novel Graph Communal Contrastive Learning (gCooL) framework to jointly learn the community partition and learn node representations in an end-to-end fashion. Specifically, the proposed gCooL consists of two components: a Dense Community Aggregation (DeCA) algorithm for community detection and a Reweighted Self-supervised Cross-contrastive (ReSC) training scheme to utilize the community information. Additionally, the real-world graphs are complex and often consist of multiple views. In this paper, we demonstrate that the proposed gCooL can also be naturally adapted to multiplex graphs. Finally, we comprehensively evaluate the proposed gCooL on a variety of real-world graphs. The experimental results show that the gCooL outperforms the state-of-the-art methods.

Proceedings of The Web Conference 2022

References in corpus (12)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Fast Graph Representation Learning with PyTorch Geometric
• Variational Graph Auto-Encoders
• GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
• Representation Learning for Attributed Multiplex Heterogeneous Network
• Deep Graph Contrastive Representation Learning
• Contrastive Multi-View Representation Learning on Graphs
• Graph Matching Networks for Learning the Similarity of Graph Structured Objects
• Deep Learning for Community Detection: Progress, Challenges and Opportunities
• GraphCL: Contrastive Self-Supervised Learning of Graph Representations
• Hierarchical Graph Convolutional Networks for Semi-supervised Node Classification
• Motif-Driven Contrastive Learning of Graph Representations

Cited by in corpus (7)

• X-GOAL: Multiplex Heterogeneous Graph Prototypical Contrastive Learning
• Revisiting Dynamic Graph Clustering via Matrix Factorization
• Causality-Aware Spatiotemporal Graph Neural Networks for Spatiotemporal Time Series Imputation
• Reliable Node Similarity Matrix Guided Contrastive Graph Clustering
• A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective
• Automated Contrastive Learning Strategy Search for Time Series
• Negative-Free Self-Supervised Gaussian Embedding of Graphs