# Meta-Path Learning for Multi-relational Graph Neural Networks

arXiv: https://arxiv.org/abs/2309.17113 · HTML: https://mlsanity.com/paper/2309.17113/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 29 Sep 2023.

## Builds on (most cited first, 19 of 19)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Graph Transformer Networks](https://mlsanity.com/paper/1911.06455/) (2019)
- [MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding](https://mlsanity.com/paper/2002.01680/) (2020)
- [DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning](https://mlsanity.com/paper/1707.06690/) (2017)
- [Deep Convolutional Networks on Graph-Structured Data](https://mlsanity.com/paper/1506.05163/) (2015)
- [Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks](https://mlsanity.com/paper/2112.14936/) (2021)
- [Cross-lingual Entity Alignment via Joint Attribute-Preserving Embedding](https://mlsanity.com/paper/1708.05045/) (2017)
- [Compositional Vector Space Models for Knowledge Base Completion](https://mlsanity.com/paper/1504.06662/) (2015)
- [Heterogeneous Graph Representation Learning with Relation Awareness](https://mlsanity.com/paper/2105.11122/) (2021)
- [Graph Transformer Networks: Learning Meta-path Graphs to Improve GNNs](https://mlsanity.com/paper/2106.06218/) (2021)
- [Attention-Based Deep Learning Framework for Human Activity Recognition with User Adaptation](https://mlsanity.com/paper/2006.03820/) (2020)
- [TEP-GNN: Accurate Execution Time Prediction of Functional Tests using Graph Neural Networks](https://mlsanity.com/paper/2208.11947/) (2022)

## Built on by (most cited first, 10 of 10)

- [No Need to Train Your RDB Foundation Model](https://mlsanity.com/paper/2602.13697/) (2026)
- [A Self-Explainable Heterogeneous GNN for Relational Deep Learning](https://mlsanity.com/paper/2412.00521/) (2024)
- [A Neuro-Symbolic Framework for Answering Graph Pattern Queries in Knowledge Graphs](https://mlsanity.com/paper/2310.04598/) (2023)
- [Bridging Theory and Practice in Link Representation with Graph Neural Networks](https://mlsanity.com/paper/2506.24018/) (2025)
- [Rethinking GNNs and Missing Features: Challenges, Evaluation and a Robust Solution](https://mlsanity.com/paper/2601.04855/) (2026)
- [Simple Path Structural Encoding for Graph Transformers](https://mlsanity.com/paper/2502.09365/) (2025)
- [RCCFormer: A Robust Crowd Counting Network Based on Transformer](https://mlsanity.com/paper/2504.04935/) (2025)
- [Analysing the Behaviour of Tree-Based Neural Networks in Regression Tasks](https://mlsanity.com/paper/2406.11437/) (2024)
- [A Benchmark Dataset for Graph Regression with Homogeneous and Multi-Relational Variants](https://mlsanity.com/paper/2505.23875/) (2025)
- [RelICL: Training-free Relational Learning with Tabular Foundation Models](https://mlsanity.com/paper/2610.01725/) (2026)

## 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.