Spiking Heterogeneous Graph Attention Networks

2025-12-31

arXiv.org

AI Summary

This work addresses the challenge of deploying heterogeneous graph neural networks on resource-constrained devices due to their structural complexity. To this end, it introduces spiking neural networks (SNNs) into heterogeneous graph learning for the first time and proposes an efficient architecture that aggregates neighbor information along meta-paths via a single shared-parameter graph convolution layer. A semantic-level attention mechanism is employed to fuse multiple semantics, and heterogeneous node features are encoded into 1-bit spike sequences. The proposed method substantially reduces model parameters, memory footprint, inference latency, and energy consumption while achieving competitive node classification performance on three real-world heterogeneous graph datasets, effectively balancing efficiency and accuracy.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

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.

Problem

• Heterogeneous Graph Neural Networks
• Computational Efficiency
• Resource Constraints
• Memory Usage
• Inference Time

Innovation

• Spiking Neural Networks
• Heterogeneous Graph Neural Networks
• Graph Attention
• Energy-Efficient Learning
• Meta-path Aggregation