pith. sign in

arxiv: 2405.11868 · v1 · pith:ZA7ZLZ4Unew · submitted 2024-05-20 · 💻 cs.LG · cs.AI· cs.CE· cs.IR· cs.SI

Towards Graph Contrastive Learning: A Survey and Beyond

classification 💻 cs.LG cs.AIcs.CEcs.IRcs.SI
keywords learninggraphcontrastivedatagraphssurveydomainsreliance
0
0 comments X
read the original abstract

In recent years, deep learning on graphs has achieved remarkable success in various domains. However, the reliance on annotated graph data remains a significant bottleneck due to its prohibitive cost and time-intensive nature. To address this challenge, self-supervised learning (SSL) on graphs has gained increasing attention and has made significant progress. SSL enables machine learning models to produce informative representations from unlabeled graph data, reducing the reliance on expensive labeled data. While SSL on graphs has witnessed widespread adoption, one critical component, Graph Contrastive Learning (GCL), has not been thoroughly investigated in the existing literature. Thus, this survey aims to fill this gap by offering a dedicated survey on GCL. We provide a comprehensive overview of the fundamental principles of GCL, including data augmentation strategies, contrastive modes, and contrastive optimization objectives. Furthermore, we explore the extensions of GCL to other aspects of data-efficient graph learning, such as weakly supervised learning, transfer learning, and related scenarios. We also discuss practical applications spanning domains such as drug discovery, genomics analysis, recommender systems, and finally outline the challenges and potential future directions in this field.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers

    cs.CR 2025-10 unverdicted novelty 7.0

    CP-GBA distills a queryable repository of promptable subgraph triggers via graph prompt learning to achieve transferable backdoor attacks on GNNs with state-of-the-art success rates across paradigms and defenses.

  2. Disentangle-then-Refine: LLM-Guided Decoupling and Structure-Aware Refinement for Graph Contrastive Learning

    cs.AI 2026-04 unverdicted novelty 6.0

    SDM-SCR uses LLMs for semantic disentanglement of signal from noise in text-attributed graphs followed by spectral consistency regularization to improve contrastive learning performance.

  3. Static and Dynamic Graph Alignment Network for Temporal Video Grounding

    cs.CV 2026-05 unverdicted novelty 5.0

    SDGAN improves temporal video grounding by jointly using static and dynamic graphs with query-clip contrastive learning and easy-to-hard progressive training.

  4. Retrieval-Augmented Generation with Graphs (GraphRAG)

    cs.IR 2024-12 unverdicted novelty 5.0

    A survey proposing a holistic GraphRAG framework with components including query processor, retriever, organizer, generator, and data source, plus domain-tailored reviews, challenges, and future directions.

  5. Graph Data Augmentation with Contrastive Learning on Covariate Distribution Shift

    cs.LG 2025-11 unverdicted novelty 4.0

    MPAIACL applies contrastive learning to generate adversarial invariant augmentations that improve GNN generalization under covariate shifts on graphs.