HeSRN: Representation Learning On Heterogeneous Graphs via Slot-Aware Retentive Network

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lu, Yifan, Zou, Ziyun, Alsinglawi, Belal, Al-Qudah, Islam, Alsmadi, Izzat, Tang, Feilong, Jiao, Pengfei, Jameel, Shoaib, Razzak, Imran
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912766640521216
author Lu, Yifan
Zou, Ziyun
Alsinglawi, Belal
Al-Qudah, Islam
Alsmadi, Izzat
Tang, Feilong
Jiao, Pengfei
Jameel, Shoaib
Razzak, Imran
author_facet Lu, Yifan
Zou, Ziyun
Alsinglawi, Belal
Al-Qudah, Islam
Alsmadi, Izzat
Tang, Feilong
Jiao, Pengfei
Jameel, Shoaib
Razzak, Imran
contents Graph Transformers have recently achieved remarkable progress in graph representation learning by capturing long-range dependencies through self-attention. However, their quadratic computational complexity and inability to effectively model heterogeneous semantics severely limit their scalability and generalization on real-world heterogeneous graphs. To address these issues, we propose HeSRN, a novel Heterogeneous Slot-aware Retentive Network for efficient and expressive heterogeneous graph representation learning. HeSRN introduces a slot-aware structure encoder that explicitly disentangles node-type semantics by projecting heterogeneous features into independent slots and aligning their distributions through slot normalization and retention-based fusion, effectively mitigating the semantic entanglement caused by forced feature-space unification in previous Transformer-based models. Furthermore, we replace the self-attention mechanism with a retention-based encoder, which models structural and contextual dependencies in linear time complexity while maintaining strong expressive power. A heterogeneous retentive encoder is further employed to jointly capture both local structural signals and global heterogeneous semantics through multi-scale retention layers. Extensive experiments on four real-world heterogeneous graph datasets demonstrate that HeSRN consistently outperforms state-of-the-art heterogeneous graph neural networks and Graph Transformer baselines on node classification tasks, achieving superior accuracy with significantly lower computational complexity.
format Preprint
id arxiv_https___arxiv_org_abs_2510_09767
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HeSRN: Representation Learning On Heterogeneous Graphs via Slot-Aware Retentive Network
Lu, Yifan
Zou, Ziyun
Alsinglawi, Belal
Al-Qudah, Islam
Alsmadi, Izzat
Tang, Feilong
Jiao, Pengfei
Jameel, Shoaib
Razzak, Imran
Machine Learning
Graph Transformers have recently achieved remarkable progress in graph representation learning by capturing long-range dependencies through self-attention. However, their quadratic computational complexity and inability to effectively model heterogeneous semantics severely limit their scalability and generalization on real-world heterogeneous graphs. To address these issues, we propose HeSRN, a novel Heterogeneous Slot-aware Retentive Network for efficient and expressive heterogeneous graph representation learning. HeSRN introduces a slot-aware structure encoder that explicitly disentangles node-type semantics by projecting heterogeneous features into independent slots and aligning their distributions through slot normalization and retention-based fusion, effectively mitigating the semantic entanglement caused by forced feature-space unification in previous Transformer-based models. Furthermore, we replace the self-attention mechanism with a retention-based encoder, which models structural and contextual dependencies in linear time complexity while maintaining strong expressive power. A heterogeneous retentive encoder is further employed to jointly capture both local structural signals and global heterogeneous semantics through multi-scale retention layers. Extensive experiments on four real-world heterogeneous graph datasets demonstrate that HeSRN consistently outperforms state-of-the-art heterogeneous graph neural networks and Graph Transformer baselines on node classification tasks, achieving superior accuracy with significantly lower computational complexity.
title HeSRN: Representation Learning On Heterogeneous Graphs via Slot-Aware Retentive Network
topic Machine Learning
url https://arxiv.org/abs/2510.09767