Transductive Spiking Graph Neural Networks for Loihi
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909182858362880 |
|---|---|
| author | Snyder, Shay Clerico, Victoria Cong, Guojing Kulkarni, Shruti Schuman, Catherine Risbud, Sumedh R. Parsa, Maryam |
| author_facet | Snyder, Shay Clerico, Victoria Cong, Guojing Kulkarni, Shruti Schuman, Catherine Risbud, Sumedh R. Parsa, Maryam |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_17048 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Transductive Spiking Graph Neural Networks for Loihi Snyder, Shay Clerico, Victoria Cong, Guojing Kulkarni, Shruti Schuman, Catherine Risbud, Sumedh R. Parsa, Maryam Emerging Technologies Machine Learning Neural and Evolutionary Computing 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. |
| title | Transductive Spiking Graph Neural Networks for Loihi |
| topic | Emerging Technologies Machine Learning Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2404.17048 |