Spiking Heterogeneous Graph Attention Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cao, Buqing, Peng, Qian, Xie, Xiang, Chen, Liang, Shi, Min, Liu, Jianxun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914234788478976
author Cao, Buqing
Peng, Qian
Xie, Xiang
Chen, Liang
Shi, Min
Liu, Jianxun
author_facet Cao, Buqing
Peng, Qian
Xie, Xiang
Chen, Liang
Shi, Min
Liu, Jianxun
contents Real-world graphs or networks are usually heterogeneous, involving multiple types of nodes and relationships. Heterogeneous graph neural networks (HGNNs) can effectively handle these diverse nodes and edges, capturing heterogeneous information within the graph, thus exhibiting outstanding performance. However, most methods of HGNNs usually involve complex structural designs, leading to problems such as high memory usage, long inference time, and extensive consumption of computing resources. These limitations pose certain challenges for the practical application of HGNNs, especially for resource-constrained devices. To mitigate this issue, we propose the Spiking Heterogeneous Graph Attention Networks (SpikingHAN), which incorporates the brain-inspired and energy-saving properties of Spiking Neural Networks (SNNs) into heterogeneous graph learning to reduce the computing cost without compromising the performance. Specifically, SpikingHAN aggregates metapath-based neighbor information using a single-layer graph convolution with shared parameters. It then employs a semantic-level attention mechanism to capture the importance of different meta-paths and performs semantic aggregation. Finally, it encodes the heterogeneous information into a spike sequence through SNNs, simulating bioinformatic processing to derive a binarized 1-bit representation of the heterogeneous graph. Comprehensive experimental results from three real-world heterogeneous graph datasets show that SpikingHAN delivers competitive node classification performance. It achieves this with fewer parameters, quicker inference, reduced memory usage, and lower energy consumption. Code is available at https://github.com/QianPeng369/SpikingHAN.
format Preprint
id arxiv_https___arxiv_org_abs_2601_02401
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Spiking Heterogeneous Graph Attention Networks
Cao, Buqing
Peng, Qian
Xie, Xiang
Chen, Liang
Shi, Min
Liu, Jianxun
Neural and Evolutionary Computing
Machine Learning
Social and Information Networks
Real-world graphs or networks are usually heterogeneous, involving multiple types of nodes and relationships. Heterogeneous graph neural networks (HGNNs) can effectively handle these diverse nodes and edges, capturing heterogeneous information within the graph, thus exhibiting outstanding performance. However, most methods of HGNNs usually involve complex structural designs, leading to problems such as high memory usage, long inference time, and extensive consumption of computing resources. These limitations pose certain challenges for the practical application of HGNNs, especially for resource-constrained devices. To mitigate this issue, we propose the Spiking Heterogeneous Graph Attention Networks (SpikingHAN), which incorporates the brain-inspired and energy-saving properties of Spiking Neural Networks (SNNs) into heterogeneous graph learning to reduce the computing cost without compromising the performance. Specifically, SpikingHAN aggregates metapath-based neighbor information using a single-layer graph convolution with shared parameters. It then employs a semantic-level attention mechanism to capture the importance of different meta-paths and performs semantic aggregation. Finally, it encodes the heterogeneous information into a spike sequence through SNNs, simulating bioinformatic processing to derive a binarized 1-bit representation of the heterogeneous graph. Comprehensive experimental results from three real-world heterogeneous graph datasets show that SpikingHAN delivers competitive node classification performance. It achieves this with fewer parameters, quicker inference, reduced memory usage, and lower energy consumption. Code is available at https://github.com/QianPeng369/SpikingHAN.
title Spiking Heterogeneous Graph Attention Networks
topic Neural and Evolutionary Computing
Machine Learning
Social and Information Networks
url https://arxiv.org/abs/2601.02401