Transductive Spiking Graph Neural Networks for Loihi

TL;DR

This paper introduces a neuromorphic, spiking graph neural network implementation optimized for Loihi 2 hardware, demonstrating efficient citation graph classification with accuracy comparable to traditional methods.

Contribution

It presents the first fully neuromorphic spiking GNN for Loihi 2, utilizing Lava Bayesian Optimization for hyperparameter tuning and achieving efficient graph classification.

Findings

Neuromorphic spiking GNN achieves comparable accuracy to floating-point models.

Lava Bayesian Optimization effectively tunes hyperparameters for neuromorphic architectures.

The approach demonstrates resource-efficient graph classification on Loihi 2.

Abstract

Graph neural networks have emerged as a specialized branch of deep learning, designed to address problems where pairwise relations between objects are crucial. Recent advancements utilize graph convolutional neural networks to extract features within graph structures. Despite promising results, these methods face challenges in real-world applications due to sparse features, resulting in inefficient resource utilization. Recent studies draw inspiration from the mammalian brain and employ spiking neural networks to model and learn graph structures. However, these approaches are limited to traditional Von Neumann-based computing systems, which still face hardware inefficiencies. In this study, we present a fully neuromorphic implementation of spiking graph neural networks designed for Loihi 2. We optimize network parameters using Lava Bayesian Optimization, a novel hyperparameter optimization system compatible with neuromorphic computing architectures. We showcase the performance benefits of combining neuromorphic Bayesian optimization with our approach for citation graph classification using fixed-precision spiking neurons. Our results demonstrate the capability of integer-precision, Loihi 2 compatible spiking neural networks in performing citation graph classification with comparable accuracy to existing floating point implementations.