VS-Graph: Scalable and Efficient Graph Classification Using Hyperdimensional Computing

2025-12-03

AI Summary

To address the high computational cost and poor deployability of Graph Neural Networks (GNNs) on resource-constrained devices for graph classification, this paper proposes an efficient graph learning framework based on Hyperdimensional Computing (HDC). The method introduces a topology-driven node identification mechanism and associative message passing, integrating spike diffusion with full high-dimensional multi-hop neighborhood aggregation—entirely eliminating backpropagation. It achieves high-performance representation learning using only 128-dimensional hypervectors. On benchmark datasets including MUTAG and DD, the approach improves accuracy by 4–5% over state-of-the-art HDC methods while accelerating training by up to 450× compared to mainstream GNNs. This work significantly narrows the gap between HDC and deep learning in both expressive power and practical utility.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Content-based information diffusion
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Graph classification is a fundamental task in domains ranging from molecular property prediction to materials design. While graph neural networks (GNNs) achieve strong performance by learning expressive representations via message passing, they incur high computational costs, limiting their scalability and deployment on resource-constrained devices. Hyperdimensional Computing (HDC), also known as Vector Symbolic Architectures (VSA), offers a lightweight, brain-inspired alternative, yet existing HDC-based graph methods typically struggle to match the predictive performance of GNNs. In this work, we propose VS-Graph, a vector-symbolic graph learning framework that narrows the gap between the efficiency of HDC and the expressive power of message passing. VS-Graph introduces a Spike Diffusion mechanism for topology-driven node identification and an Associative Message Passing scheme for multi-hop neighborhood aggregation entirely within the high-dimensional vector space. Without gradient-based optimization or backpropagation, our method achieves competitive accuracy with modern GNNs, outperforming the prior HDC baseline by 4-5% on standard benchmarks such as MUTAG and DD. It also matches or exceeds the performance of the GNN baselines on several datasets while accelerating the training by a factor of up to 450x. Furthermore, VS-Graph maintains high accuracy even with the hypervector dimensionality reduced to D=128, demonstrating robustness under aggressive dimension compression and paving the way for ultra-efficient execution on edge and neuromorphic hardware.

Problem

• Improving graph classification efficiency while maintaining competitive accuracy.
• Bridging the performance gap between lightweight HDC and powerful GNNs.
• Enabling scalable graph learning on resource-constrained edge devices.

Innovation

• Spike Diffusion for node identification
• Associative Message Passing for neighborhood aggregation
• Hyperdimensional computing without gradient optimization