English

Unifying Graph Contrastive Learning with Flexible Contextual Scopes

Machine Learning 2022-10-18 v1

Abstract

Graph contrastive learning (GCL) has recently emerged as an effective learning paradigm to alleviate the reliance on labelling information for graph representation learning. The core of GCL is to maximise the mutual information between the representation of a node and its contextual representation (i.e., the corresponding instance with similar semantic information) summarised from the contextual scope (e.g., the whole graph or 1-hop neighbourhood). This scheme distils valuable self-supervision signals for GCL training. However, existing GCL methods still suffer from limitations, such as the incapacity or inconvenience in choosing a suitable contextual scope for different datasets and building biased contrastiveness. To address aforementioned problems, we present a simple self-supervised learning method termed Unifying Graph Contrastive Learning with Flexible Contextual Scopes (UGCL for short). Our algorithm builds flexible contextual representations with tunable contextual scopes by controlling the power of an adjacency matrix. Additionally, our method ensures contrastiveness is built within connected components to reduce the bias of contextual representations. Based on representations from both local and contextual scopes, UGCL optimises a very simple contrastive loss function for graph representation learning. Essentially, the architecture of UGCL can be considered as a general framework to unify existing GCL methods. We have conducted intensive experiments and achieved new state-of-the-art performance in six out of eight benchmark datasets compared with self-supervised graph representation learning baselines. Our code has been open-sourced.

Keywords

Cite

@article{arxiv.2210.08792,
  title  = {Unifying Graph Contrastive Learning with Flexible Contextual Scopes},
  author = {Yizhen Zheng and Yu Zheng and Xiaofei Zhou and Chen Gong and Vincent CS Lee and Shirui Pan},
  journal= {arXiv preprint arXiv:2210.08792},
  year   = {2022}
}

Comments

Accepted in ICDM2022

R2 v1 2026-06-28T03:46:55.938Z