mlsanityData to 7 Oct 2026

Meta-Path Learning for Multi-relational Graph Neural Networks

arXiv 2309.17113 ↗First posted 29 Sep 2023cs.LG cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

Existing multi-relational graph neural networks use one of two strategies for identifying informative relations: either they reduce this problem to low-level weight learning, or they rely on handcrafted chains of relational dependencies, called meta-paths. However, the former approach faces challenges in the presence of many relations (e.g., knowledge graphs), while the latter requires substantial domain expertise to identify relevant meta-paths. In this work we propose a novel approach to learn meta-paths and meta-path GNNs that are highly accurate based on a small number of informative meta-paths. Key element of our approach is a scoring function for measuring the potential informativeness of a relation in the incremental construction of the meta-path. Our experimental evaluation shows that the approach manages to correctly identify relevant meta-paths even with a large number of relations, and substantially outperforms existing multi-relational GNNs on synthetic and real-world experiments.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 19 of its 39 references that are in the map. First posted on arXiv 29 Sep 2023.

Builds on

19 of 39 references.

References · 19

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  7. 2019Heterogeneous Graph Attention Networkcited by 732
  8. 2020Heterogeneous Graph Transformercited by 581
  9. 2019Graph Transformer Networkscited by 520
  10. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  11. 2017DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoningcited by 265
  12. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
7 more
  1. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
  2. 2017Cross-lingual Entity Alignment via Joint Attribute-Preserving Embeddingcited by 126
  3. 2015Compositional Vector Space Models for Knowledge Base Completioncited by 33
  4. 2021Heterogeneous Graph Representation Learning with Relation Awarenesscited by 31
  5. 2021Graph Transformer Networks: Learning Meta-path Graphs to Improve GNNscited by 22
  6. 2020Attention-Based Deep Learning Framework for Human Activity Recognition with User Adaptationcited by 5
  7. 2022TEP-GNN: Accurate Execution Time Prediction of Functional Tests using Graph Neural Networkscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 4; 2026: 3.

10 papers.

  1. 2026No Need to Train Your RDB Foundation Modelcited by 8
  2. 2024A Self-Explainable Heterogeneous GNN for Relational Deep Learningcited by 7
  3. 2023A Neuro-Symbolic Framework for Answering Graph Pattern Queries in Knowledge Graphscited by 4
  4. 2025Bridging Theory and Practice in Link Representation with Graph Neural Networkscited by 4
  5. 2025Simple Path Structural Encoding for Graph Transformerscited by 1
  6. 2025RCCFormer: A Robust Crowd Counting Network Based on Transformercited by 1
  7. 2026Rethinking GNNs and Missing Features: Challenges, Evaluation and a Robust Solutioncited by 1
  8. 2024Analysing the Behaviour of Tree-Based Neural Networks in Regression Taskscited by 0
  9. 2025A Benchmark Dataset for Graph Regression with Homogeneous and Multi-Relational Variantscited by 0
  10. 2026RelICL: Training-free Relational Learning with Tabular Foundation Modelscited by 0