mlsanityData to 7 Oct 2026

Simple and Efficient Heterogeneous Graph Neural Network

arXiv 2207.02547 ↗First posted 6 Jul 2022cs.LGcited by 71

Not on the map. Why?

Abstract (arXiv)

Heterogeneous graph neural networks (HGNNs) have powerful capability to embed rich structural and semantic information of a heterogeneous graph into node representations. Existing HGNNs inherit many mechanisms from graph neural networks (GNNs) over homogeneous graphs, especially the attention mechanism and the multi-layer structure. These mechanisms bring excessive complexity, but seldom work studies whether they are really effective on heterogeneous graphs. This paper conducts an in-depth and detailed study of these mechanisms and proposes Simple and Efficient Heterogeneous Graph Neural Network (SeHGNN). To easily capture structural information, SeHGNN pre-computes the neighbor aggregation using a light-weight mean aggregator, which reduces complexity by removing overused neighbor attention and avoiding repeated neighbor aggregation in every training epoch. To better utilize semantic information, SeHGNN adopts the single-layer structure with long metapaths to extend the receptive field, as well as a transformer-based semantic fusion module to fuse features from different metapaths. As a result, SeHGNN exhibits the characteristics of simple network structure, high prediction accuracy, and fast training speed. Extensive experiments on five real-world heterogeneous graphs demonstrate the superiority of SeHGNN over the state-of-the-arts on both accuracy and training speed.

Key facts. Cited by 71 papers in the map (data through 7 Oct 2026). Builds on 34 of its 56 references that are in the map. First posted on arXiv 6 Jul 2022.

Builds on

34 of 56 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2017Inductive Representation Learning on Large Graphscited by 6,284
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  7. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  8. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  9. 2019Simplifying Graph Convolutional Networkscited by 1,470
  10. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  11. 2016Complex Embeddings for Simple Link Predictioncited by 897
  12. 2019Heterogeneous Graph Attention Networkcited by 732
22 more
  1. 2020Heterogeneous Graph Transformercited by 581
  2. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 500
  3. 2019Composition-based Multi-Relational Graph Convolutional Networkscited by 395
  4. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 328
  5. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  6. 2020SIGN: Scalable Inception Graph Neural Networkscited by 283
  7. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
  8. 2020A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sourcescited by 126
  9. 2019Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labelscited by 111
  10. 2015A Survey of Heterogeneous Information Network Analysiscited by 109
  11. 2020Unifying Graph Convolutional Neural Networks and Label Propagationcited by 98
  12. 2020Heterogeneous Graph Neural Networks for Malicious Account Detectioncited by 95
  13. 2022Graph Attention Multi-Layer Perceptroncited by 82
  14. 2019ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networkscited by 73
  15. 2019An Attention-based Graph Neural Network for Heterogeneous Structural Learningcited by 71
  16. 2019Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoningcited by 63
  17. 2021Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced trainingcited by 54
  18. 2021Sampling methods for efficient training of graph convolutional networks: A surveycited by 40
  19. 2020Scalable Graph Neural Networks for Heterogeneous Graphscited by 31
  20. 2022Survey on Graph Neural Network Acceleration: An Algorithmic Perspectivecited by 26
  21. 2016Task-Guided and Path-Augmented Heterogeneous Network Embedding for Author Identificationcited by 18
  22. 2020Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 14; 2024: 20; 2025: 25; 2026: 12.

71 papers.

Sort:

By area:

  1. 2024Learning on Multimodal Graphs: A Surveycited by 22
  2. 2023Homophily-oriented Heterogeneous Graph Rewiringcited by 18
  3. 2023Efficient Heterogeneous Graph Learning via Random Projectioncited by 16
  4. 2024Topology-aware Embedding Memory for Continual Learning on Expanding Networkscited by 14
  5. 2024SEFraud: Graph-based Self-Explainable Fraud Detection via Interpretative Mask Learningcited by 12
  6. 2023Semantic-aware Node Synthesis for Imbalanced Heterogeneous Information Networkscited by 9
  7. 2023Mastering Long-Tail Complexity on Graphs: Characterization, Learning, and Generalizationcited by 8
  8. 2023Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomialscited by 8
  9. 2024HGAttack: Transferable Heterogeneous Graph Adversarial Attackcited by 6
  10. 2024LinkSAGE: Optimizing Job Matching Using Graph Neural Networkscited by 5
  11. 2024Task-Oriented GNNs Training on Large Knowledge Graphs for Accurate and Efficient Modelingcited by 5
  12. 2023HAGNN: Hybrid Aggregation for Heterogeneous Graph Neural Networkscited by 4
38 more
  1. 2023Long-range Meta-path Search on Large-scale Heterogeneous Graphscited by 4
  2. 2024A Unified Framework for Combinatorial Optimization Based on Graph Neural Networkscited by 4
  3. 2024RSEA-MVGNN: Multi-View Graph Neural Network with Reliable Structural Enhancement and Aggregationcited by 4
  4. 2025OmniSage: Large Scale, Multi-Entity Heterogeneous Graph Representation Learningcited by 4
  5. 2023Seq-HGNN: Learning Sequential Node Representation on Heterogeneous Graphcited by 3
  6. 2024Unleashing the Potential of Text-attributed Graphs: Automatic Relation Decomposition via Large Language Modelscited by 3
  7. 2024HeGraphAdapter: Tuning Multi-Modal Vision-Language Models with Heterogeneous Graph Adaptercited by 3
  8. 2025Adaptive Heterogeneous Graph Neural Networks: Bridging Heterophily and Heterogeneitycited by 3
  9. 2023Knowledge Enhanced Graph Neural Networks for Graph Completioncited by 2
  10. 2024Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attackcited by 2
  11. 2024HHGT: Hierarchical Heterogeneous Graph Transformer for Heterogeneous Graph Representation Learningcited by 2
  12. 2025ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusioncited by 2
  13. 2025Heterogeneous Temporal Hypergraph Neural Networkcited by 2
  14. 2025Enhancing Homophily-Heterophily Separation: Relation-Aware Learning in Heterogeneous Graphscited by 2
  15. 2025Simple and Efficient Heterogeneous Temporal Graph Neural Networkcited by 2
  16. 2026An LLM-Guided Query-Aware Inference System for GNN Models on Large Knowledge Graphscited by 2
  17. 2023Refining Latent Representations: A Generative SSL Approach for Heterogeneous Graph Learningcited by 1
  18. 2023Graph Neural Networks with a Distribution of Parametrized Graphscited by 1
  19. 2023Variational Graph Autoencoder for Heterogeneous Information Networks with Missing and Inaccurate Attributescited by 1
  20. 2023Towards Human-like Perception: Learning Structural Causal Model in Heterogeneous Graphcited by 1
  21. 2024Heterogeneous Graph Reinforcement Learning for Dependency-aware Multi-task Allocation in Spatial Crowdsourcingcited by 1
  22. 2025MAPN: Enhancing Heterogeneous Sparse Graph Representation by Mamba-based Asynchronous Aggregationcited by 1
  23. 2025Learning to Rank Critical Road Segments via Heterogeneous Graphs with Origin-Destination Flow Integrationcited by 1
  24. 2025Representation Learning with Mutual Influence of Modalities for Node Classification in Multi-Modal Heterogeneous Networkscited by 1
  25. 2025HERO: Preserving Structure and Semantics in Heterogeneous Continual Graph Learningcited by 1
  26. 2025HeTa: Relation-wise Heterogeneous Graph Foundation Attack Modelcited by 1
  27. 2025Bridging RDF Knowledge Graphs with Graph Neural Networks for Semantically-Rich Recommender Systemscited by 1
  28. 2025HGEN: Heterogeneous Graph Ensemble Networkscited by 1
  29. 2023HetCAN: A Heterogeneous Graph Cascade Attention Network with Dual-Level Awarenesscited by 0
  30. 2024Hyperedge Interaction-aware Hypergraph Neural Networkcited by 0
  31. 2024Few-shot Learning on Heterogeneous Graphs: Challenges, Progress, and Prospectscited by 0
  32. 2024Graph Dimension Attention Networks for Enterprise Credit Assessmentcited by 0
  33. 2024SiHGNN: Leveraging Properties of Semantic Graphs for Efficient HGNN Accelerationcited by 0
  34. 2024LAMP: Learnable Meta-Path Guided Adversarial Contrastive Learning for Heterogeneous Graphscited by 0
  35. 2024Deep Graph Attention Networkscited by 0
  36. 2024IMPaCT GNN: Imposing invariance with Message Passing in Chronological split Temporal Graphscited by 0
  37. 2025EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learningcited by 0
  38. 2025Incorporating Attributes and Multi-Scale Structures for Heterogeneous Graph Contrastive Learningcited by 0

50 most cited of 71 All 71 (JSON)