mlsanityData to 7 Oct 2026

A Survey of Data-Efficient Graph Learning

arXiv 2402.00447 ↗First posted 1 Feb 2024cs.LG cs.AI cs.SIcited by 18

Not on the map. Why?

Abstract (arXiv)

Graph-structured data, prevalent in domains ranging from social networks to biochemical analysis, serve as the foundation for diverse real-world systems. While graph neural networks demonstrate proficiency in modeling this type of data, their success is often reliant on significant amounts of labeled data, posing a challenge in practical scenarios with limited annotation resources. To tackle this problem, tremendous efforts have been devoted to enhancing graph machine learning performance under low-resource settings by exploring various approaches to minimal supervision. In this paper, we introduce a novel concept of Data-Efficient Graph Learning (DEGL) as a research frontier, and present the first survey that summarizes the current progress of DEGL. We initiate by highlighting the challenges inherent in training models with large labeled data, paving the way for our exploration into DEGL. Next, we systematically review recent advances on this topic from several key aspects, including self-supervised graph learning, semi-supervised graph learning, and few-shot graph learning. Also, we state promising directions for future research, contributing to the evolution of graph machine learning.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 51 of its 74 references that are in the map. First posted on arXiv 1 Feb 2024.

Builds on

51 of 74 references.

References · 51

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  5. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  6. 2018Deep Graph Infomaxcited by 1,101
  7. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  8. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  9. 2021Graph Contrastive Learning Automatedcited by 287
  10. 2019Attributed Graph Clustering: A Deep Attentional Embedding Approachcited by 149
  11. 2020Structural Deep Clustering Networkcited by 145
  12. 2021Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learningcited by 130
38 more
  1. 2020Node Similarity Preserving Graph Convolutional Networkscited by 112
  2. 2020Self-supervised Learning on Graphs: Deep Insights and New Directioncited by 108
  3. 2019Meta-GNN: On Few-shot Node Classification in Graph Meta-learningcited by 105
  4. 2022How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervisioncited by 102
  5. 2021Deep Graph Clustering via Dual Correlation Reductioncited by 97
  6. 2020Graph Prototypical Networks for Few-shot Learning on Attributed Networkscited by 90
  7. 2019Learning Graph Embedding with Adversarial Training Methodscited by 84
  8. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
  9. 2020Deep Fusion Clustering Networkcited by 71
  10. 2019Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolutioncited by 67
  11. 2022Empowering Graph Representation Learning with Test-Time Graph Transformationcited by 66
  12. 2019Graph Few-shot Learning via Knowledge Transfercited by 63
  13. 2020ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Predictioncited by 58
  14. 2022Simple Contrastive Graph Clusteringcited by 56
  15. 2019Semi-Supervised Graph Classification: A Hierarchical Graph Perspectivecited by 55
  16. 2023CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classificationcited by 46
  17. 2023Virtual Node Tuning for Few-shot Node Classificationcited by 46
  18. 2020Adversarial Deep Network Embedding for Cross-network Node Classificationcited by 44
  19. 2022Non-IID Transfer Learning on Graphscited by 43
  20. 2021Graph Few-shot Class-incremental Learningcited by 40
  21. 2020Self-Supervised Graph Representation Learning via Global Context Predictioncited by 38
  22. 2021Graph Domain Adaptation: A Generative Viewcited by 35
  23. 2020Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measurescited by 31
  24. 2021Proof of the Theory-to-Practice Gap in Deep Learning via Sampling Complexity bounds for Neural Network Approximation Spacescited by 30
  25. 2022Graph Few-shot Learning with Task-specific Structurescited by 26
  26. 2019Pre-Training Graph Neural Networks for Generic Structural Feature Extractioncited by 24
  27. 2022CGC: Contrastive Graph Clustering for Community Detection and Trackingcited by 21
  28. 2022GLCC: A General Framework for Graph-Level Clusteringcited by 21
  29. 2023TGNN: A Joint Semi-supervised Framework for Graph-level Classificationcited by 19
  30. 2020CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learningcited by 18
  31. 2021Self-supervised Contrastive Attributed Graph Clusteringcited by 18
  32. 2022Label-invariant Augmentation for Semi-Supervised Graph Classificationcited by 18
  33. 2022KGNN: Harnessing Kernel-based Networks for Semi-supervised Graph Classificationcited by 18
  34. 2022Test-Time Training for Graph Neural Networkscited by 17
  35. 2021Hybrid Graph Neural Networks for Few-Shot Learningcited by 15
  36. 2023Contrastive Graph Clustering in Curvature Spacescited by 15
  37. 2023Towards Semi-supervised Universal Graph Classificationcited by 15
  38. 2023Redundancy-Free Self-Supervised Relational Learning for Graph Clusteringcited by 8

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 7; 2026: 2.

18 papers.

Sort:

By area:

  1. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
  2. 2024COMAE: COMprehensive Attribute Exploration for Zero-shot Hashingcited by 16
  3. 2024Unveiling Delay Effects in Traffic Forecasting: A Perspective from Spatial-Temporal Delay Differential Equationscited by 11
  4. 2024Hypergraph-enhanced Dual Semi-supervised Graph Classificationcited by 8
  5. 2024Semi-supervised Fine-tuning for Large Language Modelscited by 8
  6. 2025Few-Shot Graph Out-of-Distribution Detection with LLMscited by 6
  7. 2026ScienceDB AI: An LLM-Driven Agentic Recommender System for Large-Scale Scientific Data Sharing Servicescited by 5
  8. 2024DisenSemi: Semi-supervised Graph Classification via Disentangled Representation Learningcited by 3
  9. 2024COOL: A Conjoint Perspective on Spatio-Temporal Graph Neural Network for Traffic Forecastingcited by 2
  10. 2024DisCo: Graph-Based Disentangled Contrastive Learning for Cold-Start Cross-Domain Recommendationcited by 2
  11. 2025Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptationcited by 2
  12. 2024Towards Graph Prompt Learning: A Survey and Beyondcited by 1
6 more
  1. 2025Higher-Order Regularization Learning on Hypergraphscited by 1
  2. 2025Subset-Contrastive Multi-Omics Network Embeddingcited by 0
  3. 2025Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly Detectioncited by 0
  4. 2025Cross-Domain Diffusion with Progressive Alignment for Efficient Adaptive Retrievalcited by 0
  5. 2025A Deep Latent Factor Graph Clustering with Fairness-Utility Trade-off Perspectivecited by 0
  6. 2026Data-Efficient Agentic Graph Domain Adaptation via Reliability-Aware Prototype Learningcited by 0