CiliaGraph: Enabling Expression-enhanced Hyper-Dimensional Computation in Ultra-Lightweight and One-Shot Graph Classification on Edge

TL;DR

CiliaGraph is a lightweight, hyper-dimensional computing-based graph classification method that significantly reduces resource usage and training time on edge devices while maintaining accuracy.

Contribution

It introduces a novel node encoding strategy and explores orthogonality-dimensionality relationships to enhance efficiency and expressiveness in HDC-based graph classification.

Findings

Reduces memory usage by up to 2341 times

Speeds up training by up to 313 times

Maintains comparable accuracy to state-of-the-art GNNs

Abstract

Graph Neural Networks (GNNs) are computationally demanding and inefficient when applied to graph classification tasks in resource-constrained edge scenarios due to their inherent process, involving multiple rounds of forward and backward propagation. As a lightweight alternative, Hyper-Dimensional Computing (HDC), which leverages high-dimensional vectors for data encoding and processing, offers a more efficient solution by addressing computational bottleneck. However, current HDC methods primarily focus on static graphs and neglect to effectively capture node attributes and structural information, which leads to poor accuracy. In this work, we propose CiliaGraph, an enhanced expressive yet ultra-lightweight HDC model for graph classification. This model introduces a novel node encoding strategy that preserves relative distance isomorphism for accurate node connection representation. In addition, node distances are utilized as edge weights for information aggregation, and the encoded node attributes and structural information are concatenated to obtain a comprehensive graph representation. Furthermore, we explore the relationship between orthogonality and dimensionality to reduce the dimensions, thereby further enhancing computational efficiency. Compared to the SOTA GNNs, extensive experiments show that CiliaGraph reduces memory usage and accelerates training speed by an average of 292 times(up to 2341 times) and 103 times(up to 313 times) respectively while maintaining comparable accuracy.