Molecular Classification Using Hyperdimensional Graph Classification

TL;DR

This paper presents a hyperdimensional computing approach for molecular graph classification that achieves comparable accuracy to state-of-the-art models while significantly improving training and inference speed, especially in chemoinformatics applications.

Contribution

It introduces an HDC-based graph classification model that outperforms previous hyperdimensional methods and accelerates training and inference compared to GNNs and WL kernels.

Findings

Achieves comparable AUC to GNNs and WL kernels.

Provides 40x faster training and 15x faster inference.

Outperforms previous hyperdimensional graph learning methods.

Abstract

Our work introduces an innovative approach to graph learning by leveraging Hyperdimensional Computing. Graphs serve as a widely embraced method for conveying information, and their utilization in learning has gained significant attention. This is notable in the field of chemoinformatics, where learning from graph representations plays a pivotal role. An important application within this domain involves the identification of cancerous cells across diverse molecular structures. We propose an HDC-based model that demonstrates comparable Area Under the Curve results when compared to state-of-the-art models like Graph Neural Networks (GNNs) or the Weisfieler-Lehman graph kernel (WL). Moreover, it outperforms previously proposed hyperdimensional computing graph learning methods. Furthermore, it achieves noteworthy speed enhancements, boasting a 40x acceleration in the training phase and a 15x improvement in inference time compared to GNN and WL models. This not only underscores the efficacy of the HDC-based method, but also highlights its potential for expedited and resource-efficient graph learning.