Data to 7 Oct 2026

Graph Meta Learning via Local Subgraphs

arXiv 2006.07889 ↗First posted 14 Jun 2020cs.LG stat.MLcited by 89

Not on the map. Why?

Abstract (arXiv)

Prevailing methods for graphs require abundant label and edge information for learning. When data for a new task are scarce, meta-learning can learn from prior experiences and form much-needed inductive biases for fast adaption to new tasks. Here, we introduce G-Meta, a novel meta-learning algorithm for graphs. G-Meta uses local subgraphs to transfer subgraph-specific information and learn transferable knowledge faster via meta gradients. G-Meta learns how to quickly adapt to a new task using only a handful of nodes or edges in the new task and does so by learning from data points in other graphs or related, albeit disjoint label sets. G-Meta is theoretically justified as we show that the evidence for a prediction can be found in the local subgraph surrounding the target node or edge. Experiments on seven datasets and nine baseline methods show that G-Meta outperforms existing methods by up to 16.3%. Unlike previous methods, G-Meta successfully learns in challenging, few-shot learning settings that require generalization to completely new graphs and never-before-seen labels. Finally, G-Meta scales to large graphs, which we demonstrate on a new Tree-of-Life dataset comprising of 1,840 graphs, a two-orders of magnitude increase in the number of graphs used in prior work.

Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 21; 2023: 22; 2024: 18; 2025: 9; 2026: 9.

89 papers.

Sort:

By area:

2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 166
2021From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awarenesscited by 154
2021Nested Graph Neural Networkscited by 136
2021InfoGCL: Information-Aware Graph Contrastive Learningcited by 105
2023PRODIGY: Enabling In-context Learning Over Graphscited by 97
2021Graph Representation Learning in Biomedicinecited by 79
2023Virtual Node Tuning for Few-shot Node Classificationcited by 46
2022Task-Adaptive Few-shot Node Classificationcited by 43
2023Generalized Graph Prompt: Toward a Unification of Pre-Training and Downstream Tasks on Graphscited by 39
2022Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learningcited by 28
2022Graph Few-shot Learning with Task-specific Structurescited by 26
2022Transductive Linear Probing: A Novel Framework for Few-Shot Node Classificationcited by 24

38 more

2023Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphscited by 23
2022FAITH: Few-Shot Graph Classification with Hierarchical Task Graphscited by 22
2022Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representationcited by 21
2022Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphscited by 21
2022Informative Pseudo-Labeling for Graph Neural Networks with Few Labelscited by 19
2022Cross-Domain Few-Shot Graph Classificationcited by 19
2022Interpreting Unfairness in Graph Neural Networks via Training Node Attributioncited by 18
2023A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directionscited by 15
2022kHGCN: Tree-likeness Modeling via Continuous and Discrete Curvature Learningcited by 14
2023Few-shot Node Classification with Extremely Weak Supervisioncited by 14
2025MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learningcited by 13
2022Few-Shot Learning on Graphscited by 11
2022Toward Robust Graph Semi-Supervised Learning against Extreme Data Scarcitycited by 11
2023Contrastive Meta-Learning for Few-shot Node Classificationcited by 11
2024Pre-Training and Prompting for Few-Shot Node Classification on Text-Attributed Graphscited by 11
2021Structure Inducing Pre-Trainingcited by 10
2021Data Considerations in Graph Representation Learning for Supply Chain Networkscited by 10
2022Supervised Graph Contrastive Learning for Few-shot Node Classificationcited by 9
2024Enhancing Trust in LLMs: Algorithms for Comparing and Interpreting LLMscited by 9
2022Self-supervised Graphs for Audio Representation Learning with Limited Labeled Datacited by 8
2023SUREL+: Moving from Walks to Sets for Scalable Subgraph-based Graph Representation Learningcited by 8
2023Task-Equivariant Graph Few-shot Learningcited by 8
2024Urban Region Pre-training and Prompting: A Graph-based Approachcited by 8
2021Meta-Learning with Graph Neural Networks: Methods and Applicationscited by 7
2021Deeper-GXX: Deepening Arbitrary GNNscited by 7
2022SHINE: SubHypergraph Inductive Neural nEtworkcited by 7
2023Edge-free but Structure-aware: Prototype-Guided Knowledge Distillation from GNNs to MLPscited by 7
2024Meta-GPS++: Enhancing Graph Meta-Learning with Contrastive Learning and Self-Trainingcited by 7
2021Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learningcited by 6
2023Bi-level Contrastive Learning for Knowledge-Enhanced Molecule Representationscited by 6
2024Few-Shot Causal Representation Learning for Out-of-Distribution Generalization on Heterogeneous Graphscited by 6
2025Enhancing Unsupervised Graph Few-shot Learning via Set Functions and Optimal Transportcited by 6
2023Hyperbolic Graph Neural Networks at Scale: A Meta Learning Approachcited by 5
2024A Survey of Few-Shot Learning on Graphs: from Meta-Learning to Pre-Training and Prompt Learningcited by 5
2024Multi-View Subgraph Neural Networks: Self-Supervised Learning with Scarce Labeled Datacited by 5
2025Dual-level Mixup for Graph Few-shot Learning with Fewer Taskscited by 5
2022Few-Shot Semantic Relation Prediction across Heterogeneous Graphscited by 4
2022Graph Learning and Its Advancements on Large Language Models: A Holistic Surveycited by 4

50 most cited of 89 All 89 (JSON)