Shay Snyder, Victoria Clerico, Guojing Cong, Shruti Kulkarni, Catherine Schuman, Sumedh Risbud and Maryam Parsa

June, 2024

GLSVLSI - Great Lakes Symposium on VLSI

https://dl.acm.org/doi/abs/10.1145/3649476.3660366

PDF not available yet, or is only available from the conference/journal publisher.

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.

Citation Information

Text

author      S. Snyder and V. Clerico and G. Cong and S. Kulkarni and C. D. Schuman and S. Risbud and M. Parsa
title       Transductive Spiking Graph Neural Networks for {Loihi}
booktitle   GLSVLSI - Great Lakes Symposium on VLSI
month       June
year        2024
pages       608-613
publisher   ACM
url         https://dl.acm.org/doi/abs/10.1145/3649476.3660366
doi         10.1145/3649476.3660366

Bibtex

@INPROCEEDINGS{drf:23:rfam,
    author = "S. Snyder and V. Clerico and G. Cong and S. Kulkarni and C. D. Schuman and S. Risbud and M. Parsa",
    title = "Transductive Spiking Graph Neural Networks for {Loihi}",
    booktitle = "GLSVLSI - Great Lakes Symposium on VLSI",
    month = "June",
    year = "2024",
    pages = "608-613",
    publisher = "ACM",
    url = "https://dl.acm.org/doi/abs/10.1145/3649476.3660366",
    doi = "10.1145/3649476.3660366"
}