# Graph Meta Learning via Local Subgraphs

arXiv: https://arxiv.org/abs/2006.07889 · HTML: https://mlsanity.com/paper/2006.07889/

## Key facts

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

## Built on by (most cited first, 30 of 89)

- [GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks](https://mlsanity.com/paper/2302.08043/) (2023)
- [From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness](https://mlsanity.com/paper/2110.03753/) (2021)
- [Nested Graph Neural Networks](https://mlsanity.com/paper/2110.13197/) (2021)
- [InfoGCL: Information-Aware Graph Contrastive Learning](https://mlsanity.com/paper/2110.15438/) (2021)
- [PRODIGY: Enabling In-context Learning Over Graphs](https://mlsanity.com/paper/2305.12600/) (2023)
- [Graph Representation Learning in Biomedicine](https://mlsanity.com/paper/2104.04883/) (2021)
- [Virtual Node Tuning for Few-shot Node Classification](https://mlsanity.com/paper/2306.06063/) (2023)
- [Task-Adaptive Few-shot Node Classification](https://mlsanity.com/paper/2206.11972/) (2022)
- [Generalized Graph Prompt: Toward a Unification of Pre-Training and Downstream Tasks on Graphs](https://mlsanity.com/paper/2311.15317/) (2023)
- [Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning](https://mlsanity.com/paper/2202.13538/) (2022)
- [Graph Few-shot Learning with Task-specific Structures](https://mlsanity.com/paper/2210.12130/) (2022)
- [Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification](https://mlsanity.com/paper/2212.05606/) (2022)
- [Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs](https://mlsanity.com/paper/2310.09872/) (2023)
- [FAITH: Few-Shot Graph Classification with Hierarchical Task Graphs](https://mlsanity.com/paper/2205.02435/) (2022)
- [Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representation](https://mlsanity.com/paper/2205.13954/) (2022)
- [Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphs](https://mlsanity.com/paper/2210.08654/) (2022)
- [Informative Pseudo-Labeling for Graph Neural Networks with Few Labels](https://mlsanity.com/paper/2201.07951/) (2022)
- [Cross-Domain Few-Shot Graph Classification](https://mlsanity.com/paper/2201.08265/) (2022)
- [Interpreting Unfairness in Graph Neural Networks via Training Node Attribution](https://mlsanity.com/paper/2211.14383/) (2022)
- [A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directions](https://mlsanity.com/paper/2308.13821/) (2023)
- [kHGCN: Tree-likeness Modeling via Continuous and Discrete Curvature Learning](https://mlsanity.com/paper/2212.01793/) (2022)
- [Few-shot Node Classification with Extremely Weak Supervision](https://mlsanity.com/paper/2301.02708/) (2023)
- [MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning](https://mlsanity.com/paper/2505.16225/) (2025)
- [Few-Shot Learning on Graphs](https://mlsanity.com/paper/2203.09308/) (2022)
- [Toward Robust Graph Semi-Supervised Learning against Extreme Data Scarcity](https://mlsanity.com/paper/2208.12422/) (2022)
- [Contrastive Meta-Learning for Few-shot Node Classification](https://mlsanity.com/paper/2306.15154/) (2023)
- [Pre-Training and Prompting for Few-Shot Node Classification on Text-Attributed Graphs](https://mlsanity.com/paper/2407.15431/) (2024)
- [Structure Inducing Pre-Training](https://mlsanity.com/paper/2103.10334/) (2021)
- [Data Considerations in Graph Representation Learning for Supply Chain Networks](https://mlsanity.com/paper/2107.10609/) (2021)
- [Supervised Graph Contrastive Learning for Few-shot Node Classification](https://mlsanity.com/paper/2203.15936/) (2022)

## 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.