# Meta-Graph: Few Shot Link Prediction via Meta Learning

arXiv: https://arxiv.org/abs/1912.09867 · HTML: https://mlsanity.com/paper/1912.09867/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2019.

## Built on by (most cited first, 24 of 24)

- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Meta Learning for Natural Language Processing: A Survey](https://mlsanity.com/paper/2205.01500/) (2022)
- [Hyper Meta-Path Contrastive Learning for Multi-Behavior Recommendation](https://mlsanity.com/paper/2109.02859/) (2021)
- [Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphs](https://mlsanity.com/paper/2210.08654/) (2022)
- [Cross-Domain Few-Shot Graph Classification](https://mlsanity.com/paper/2201.08265/) (2022)
- [Trans4E: Link Prediction on Scholarly Knowledge Graphs](https://mlsanity.com/paper/2107.03297/) (2021)
- [Few-Shot Learning on Graphs](https://mlsanity.com/paper/2203.09308/) (2022)
- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [Meta-Learning with Graph Neural Networks: Methods and Applications](https://mlsanity.com/paper/2103.00137/) (2021)
- [How Neural Processes Improve Graph Link Prediction](https://mlsanity.com/paper/2109.14894/) (2021)
- [Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning](https://mlsanity.com/paper/2103.00771/) (2021)
- [A Survey On Few-shot Knowledge Graph Completion with Structural and Commonsense Knowledge](https://mlsanity.com/paper/2301.01172/) (2023)
- [Task and Model Agnostic Adversarial Attack on Graph Neural Networks](https://mlsanity.com/paper/2112.13267/) (2021)
- [Graph Representation Learning for Multi-Task Settings: a Meta-Learning Approach](https://mlsanity.com/paper/2201.03326/) (2022)
- [Hyperbolic Graph Neural Networks at Scale: A Meta Learning Approach](https://mlsanity.com/paper/2310.18918/) (2023)
- [Structure-Enhanced Meta-Learning For Few-Shot Graph Classification](https://mlsanity.com/paper/2103.03547/) (2021)
- [You Only Transfer What You Share: Intersection-Induced Graph Transfer Learning for Link Prediction](https://mlsanity.com/paper/2302.14189/) (2023)
- [Dynamic Link Prediction for New Nodes in Temporal Graph Networks](https://mlsanity.com/paper/2310.09787/) (2023)
- [Concept-free Causal Disentanglement with Variational Graph Auto-Encoder](https://mlsanity.com/paper/2311.10638/) (2023)
- [Introducing New Node Prediction in Graph Mining: Predicting All Links from Isolated Nodes with Graph Neural Networks](https://mlsanity.com/paper/2401.05468/) (2024)
- [TMetaNet: Topological Meta-Learning Framework for Dynamic Link Prediction](https://mlsanity.com/paper/2506.00453/) (2025)
- [Meta-Reinforcement Learning via Buffering Graph Signatures for Live Video Streaming Events](https://mlsanity.com/paper/2111.09412/) (2021)
- [Simple Rule Injection for ComplEx Embeddings](https://mlsanity.com/paper/2308.03269/) (2023)
- [FairExpand: Individual Fairness on Graphs with Partial Similarity Information](https://mlsanity.com/paper/2512.18180/) (2025)

## Abstract (arXiv)

We consider the task of few shot link prediction on graphs. The goal is to learn from a distribution over graphs so that a model is able to quickly infer missing edges in a new graph after a small amount of training. We show that current link prediction methods are generally ill-equipped to handle this task. They cannot effectively transfer learned knowledge from one graph to another and are unable to effectively learn from sparse samples of edges. To address this challenge, we introduce a new gradient-based meta learning framework, Meta-Graph. Our framework leverages higher-order gradients along with a learned graph signature function that conditionally generates a graph neural network initialization. Using a novel set of few shot link prediction benchmarks, we show that Meta-Graph can learn to quickly adapt to a new graph using only a small sample of true edges, enabling not only fast adaptation but also improved results at convergence.