mlsanityData to 13 Oct 2026

Long-range Meta-path Search on Large-scale Heterogeneous Graphs

arXiv 2307.08430 ↗First posted 17 Jul 2023cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Utilizing long-range dependency, a concept extensively studied in homogeneous graphs, remains underexplored in heterogeneous graphs, especially on large ones, posing two significant challenges: Reducing computational costs while maximizing effective information utilization in the presence of heterogeneity, and overcoming the over-smoothing issue in graph neural networks. To address this gap, we investigate the importance of different meta-paths and introduce an automatic framework for utilizing long-range dependency on heterogeneous graphs, denoted as Long-range Meta-path Search through Progressive Sampling (LMSPS). Specifically, we develop a search space with all meta-paths related to the target node type. By employing a progressive sampling algorithm, LMSPS dynamically shrinks the search space with hop-independent time complexity. Through a sampling evaluation strategy, LMSPS conducts a specialized and effective meta-path selection, leading to retraining with only effective meta-paths, thus mitigating costs and over-smoothing. Extensive experiments across diverse heterogeneous datasets validate LMSPS's capability in discovering effective long-range meta-paths, surpassing state-of-the-art methods. Our code is available at https://github.com/JHL-HUST/LMSPS.

Key facts. Cited by 4 papers in the map (data through 13 Oct 2026). Builds on 46 of its 67 references that are in the map. First posted on arXiv 17 Jul 2023.

Builds on

46 of 67 references.

References · 46

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,223
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,318
  3. 2017Graph Attention Networkscited by 8,888
  4. 2017Inductive Representation Learning on Large Graphscited by 6,303
  5. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,157
  6. 2018DARTS: Differentiable Architecture Searchcited by 1,789
  7. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,689
  8. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,442
  9. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,142
  10. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  11. 2019Heterogeneous Graph Attention Networkcited by 733
  12. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 629
34 more
  1. 2020Heterogeneous Graph Transformercited by 582
  2. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 541
  3. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  4. 2019Graph Transformer Networkscited by 522
  5. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 503
  6. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 412
  7. 2017Large-Scale Evolution of Image Classifierscited by 348
  8. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 329
  9. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  10. 2018SNAS: Stochastic Neural Architecture Searchcited by 288
  11. 2019Searching for A Robust Neural Architecture in Four GPU Hourscited by 259
  12. 2020Combining Label Propagation and Simple Models Out-performs Graph Neural Networkscited by 200
  13. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
  14. 2017Genetic CNNcited by 124
  15. 2019Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labelscited by 111
  16. 2022Not too little, not too much: a theoretical analysis of graph (over)smoothingcited by 106
  17. 2020Unifying Graph Convolutional Neural Networks and Label Propagationcited by 98
  18. 2022A Generalization of ViT/MLP-Mixer to Graphscited by 93
  19. 2021Rethinking Architecture Selection in Differentiable NAScited by 92
  20. 2022Graph Attention Multi-Layer Perceptroncited by 83
  21. 2019An Attention-based Graph Neural Network for Heterogeneous Structural Learningcited by 71
  22. 2022Simple and Efficient Heterogeneous Graph Neural Networkcited by 71
  23. 2021Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced trainingcited by 54
  24. 2023Scaling MLPs: A Tale of Inductive Biascited by 37
  25. 2023HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformercited by 35
  26. 2020DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networkscited by 34
  27. 2019Efficient Neural Architecture Search via Proximal Iterationscited by 31
  28. 2020Scalable Graph Neural Networks for Heterogeneous Graphscited by 31
  29. 2022DynaMixer: A Vision MLP Architecture with Dynamic Mixingcited by 28
  30. 2021Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networkscited by 22
  31. 2021Genetic Meta-Structure Search for Recommendation on Heterogeneous Information Networkcited by 9
  32. 2022Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Networkcited by 8
  33. 2021Automatic Meta-Path Discovery for Effective Graph-Based Recommendationcited by 5
  34. 2022Differentiable Meta Multigraph Search with Partial Message Propagation on Heterogeneous Information Networkscited by 5

Built on by

Cited by year (2026 to 13 Oct)

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

4 papers.

  1. 2024HeteGraph-Mamba: Heterogeneous Graph Learning via Selective State Space Modelcited by 3
  2. 2025ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusioncited by 2
  3. 2024Addressing Graph Heterogeneity and Heterophily from A Spectral Perspectivecited by 1
  4. 2026AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagationcited by 0