TAHAN: Type-Aware Heterogeneous Graph AttentionNeural Networks
Authors:
- Amine LakhderALAmine Lakhder
- Fahd KalloubiFKFahd Kalloubi
- Abdelhak BoulaalamABAbdelhak Boulaalam
- Lamiae AziziLALamiae Azizi
Preprint
- 16 May 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Learning from heterogeneous graphs remains challenging when structural complexity surpasses the modeling capacity of existing heterogeneous graph neural networks (HGNNs). Although current HGNNs capture structural and semantic relations, they typically treat node types as static categorical labels and overlook the contextual influence these types exert during message passing. Metapath-based models further restrict aggregation to the endpoints of a metapath, neglecting the semantic contribution of intermediate node types. As a result, they underexploit type-dependent contextual signals and often struggle in settings with sparse or weakly connected entity types. We propose TAHAN (Type-Aware Heterogeneous Graph Attention Network), a model that explicitly incorporates type-sensitive and context-dependent information into heterogeneous neighborhood aggregation. TAHAN first gathers neighbors across full metapath instances and multiple neighborhood levels, organizing them into type-specific neighborhoods. It then applies a two-stage attention mechanism: type-specific attention to capture contributions from nodes within the same type, followed by type-aware attention to model interactions across different types. The resulting representations fuse these signals into expressive, type-sensitive node embeddings. Experiments on multiple benchmarks show that TAHAN consistently outperforms state-of-the-art HGNNs. Component-level analyses further demonstrate the interpretability and practical value of type-aware modeling, offering insights for future research.Keywords
This publication has 15 references indexed in Scilit:
- A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and ExplainabilityMachine Intelligence Research, 2024
- Multi-view Heterogeneous Graph Neural Networks for Node ClassificationData Science and Engineering, 2024
- Hierarchical Contrastive Learning Enhanced Heterogeneous Graph Neural NetworkIEEE Transactions on Knowledge and Data Engineering, 2023
- Geometric Deep Learning for Protein–Protein Interaction PredictionsIEEE Access, 2022
- A Comprehensive Survey of Graph Neural Networks for Knowledge GraphsIEEE Access, 2022
- A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and SourcesIEEE Transactions on Big Data, 2022
- Heterogeneous Network Representation Learning: A Unified Framework With Survey and BenchmarkIEEE Transactions on Knowledge and Data Engineering, 2020
- Heterogeneous Information Network Embedding for RecommendationIEEE Transactions on Knowledge and Data Engineering, 2018
- Mining heterogeneous information networksACM SIGKDD Explorations Newsletter, 2013
- The Graph Neural Network ModelIEEE Transactions on Neural Networks, 2008