mlsanityData to 14 Oct 2026

Meta-Graph: Few Shot Link Prediction via Meta Learning

arXiv 1912.09867 ↗First posted 20 Dec 2019cs.LG cs.SI stat.MLcited by 24

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 6; 2023: 6; 2024: 1; 2025: 2.

24 papers.

Sort:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
  2. 2022Meta Learning for Natural Language Processing: A Surveycited by 26
  3. 2021Hyper Meta-Path Contrastive Learning for Multi-Behavior Recommendationcited by 21
  4. 2022Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphscited by 21
  5. 2022Cross-Domain Few-Shot Graph Classificationcited by 19
  6. 2021Trans4E: Link Prediction on Scholarly Knowledge Graphscited by 13
  7. 2022Few-Shot Learning on Graphscited by 11
  8. 2021What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Datacited by 10
  9. 2021Meta-Learning with Graph Neural Networks: Methods and Applicationscited by 7
  10. 2021How Neural Processes Improve Graph Link Predictioncited by 7
  11. 2021Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learningcited by 6
  12. 2023A Survey On Few-shot Knowledge Graph Completion with Structural and Commonsense Knowledgecited by 6
12 more
  1. 2021Task and Model Agnostic Adversarial Attack on Graph Neural Networkscited by 5
  2. 2022Graph Representation Learning for Multi-Task Settings: a Meta-Learning Approachcited by 5
  3. 2023Hyperbolic Graph Neural Networks at Scale: A Meta Learning Approachcited by 5
  4. 2021Structure-Enhanced Meta-Learning For Few-Shot Graph Classificationcited by 4
  5. 2023You Only Transfer What You Share: Intersection-Induced Graph Transfer Learning for Link Predictioncited by 4
  6. 2023Dynamic Link Prediction for New Nodes in Temporal Graph Networkscited by 1
  7. 2023Concept-free Causal Disentanglement with Variational Graph Auto-Encodercited by 1
  8. 2024Introducing New Node Prediction in Graph Mining: Predicting All Links from Isolated Nodes with Graph Neural Networkscited by 1
  9. 2025TMetaNet: Topological Meta-Learning Framework for Dynamic Link Predictioncited by 1
  10. 2021Meta-Reinforcement Learning via Buffering Graph Signatures for Live Video Streaming Eventscited by 0
  11. 2023Simple Rule Injection for ComplEx Embeddingscited by 0
  12. 2025FairExpand: Individual Fairness on Graphs with Partial Similarity Informationcited by 0