mlsanityData to 7 Oct 2026

Few-Shot Semantic Relation Prediction across Heterogeneous Graphs

arXiv 2207.05068 ↗First posted 11 Jul 2022cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Semantic relation prediction aims to mine the implicit relationships between objects in heterogeneous graphs, which consist of different types of objects and different types of links. In real-world scenarios, new semantic relations constantly emerge and they typically appear with only a few labeled data. Since a variety of semantic relations exist in multiple heterogeneous graphs, the transferable knowledge can be mined from some existing semantic relations to help predict the new semantic relations with few labeled data. This inspires a novel problem of few-shot semantic relation prediction across heterogeneous graphs. However, the existing methods cannot solve this problem because they not only require a large number of labeled samples as input, but also focus on a single graph with a fixed heterogeneity. Targeting this novel and challenging problem, in this paper, we propose a Meta-learning based Graph neural network for Semantic relation prediction, named MetaGS. Firstly, MetaGS decomposes the graph structure between objects into multiple normalized subgraphs, then adopts a two-view graph neural network to capture local heterogeneous information and global structure information of these subgraphs. Secondly, MetaGS aggregates the information of these subgraphs with a hyper-prototypical network, which can learn from existing semantic relations and adapt to new semantic relations. Thirdly, using the well-initialized two-view graph neural network and hyper-prototypical network, MetaGS can effectively learn new semantic relations from different graphs while overcoming the limitation of few labeled data. Extensive experiments on three real-world datasets have demonstrated the superior performance of MetaGS over the state-of-the-art methods.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 26 of its 50 references that are in the map. First posted on arXiv 11 Jul 2022.

Builds on

26 of 50 references.

References · 26

  1. 2017Graph Attention Networkscited by 8,854
  2. 2017Inductive Representation Learning on Large Graphscited by 6,284
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  6. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  7. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  8. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  9. 2018Link Prediction Based on Graph Neural Networkscited by 829
  10. 2019Heterogeneous Graph Attention Networkcited by 732
  11. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  12. 2019Inductive Relation Prediction by Subgraph Reasoningcited by 237
14 more
  1. 2020A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sourcescited by 126
  2. 2019Meta-GNN: On Few-shot Node Classification in Graph Meta-learningcited by 105
  3. 2020Graph Prototypical Networks for Few-shot Learning on Attributed Networkscited by 90
  4. 2020Graph Meta Learning via Local Subgraphscited by 89
  5. 2019Graph Few-shot Learning via Knowledge Transfercited by 63
  6. 2019Few-Shot Knowledge Graph Completioncited by 63
  7. 2020Interpretable and Efficient Heterogeneous Graph Convolutional Networkcited by 48
  8. 2021Dynamic Network Embedding Surveycited by 44
  9. 2021Graph Few-shot Class-incremental Learningcited by 40
  10. 2022Bi-CLKT: Bi-Graph Contrastive Learning based Knowledge Tracingcited by 23
  11. 2020Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embeddingcited by 19
  12. 2020Self-Supervised Learning of Contextual Embeddings for Link Prediction in Heterogeneous Networkscited by 17
  13. 2022Few-Shot Learning on Graphscited by 11
  14. 2020Top-k Socio-Spatial Co-engaged Location Selection for Social Userscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2.

4 papers.

  1. 2024Few-Shot Causal Representation Learning for Out-of-Distribution Generalization on Heterogeneous Graphscited by 6
  2. 2023Cross-heterogeneity Graph Few-shot Learningcited by 3
  3. 2023Variational Counterfactual Prediction under Runtime Domain Corruptioncited by 0
  4. 2024Few-shot Learning on Heterogeneous Graphs: Challenges, Progress, and Prospectscited by 0