# Hybrid variable spiking graph neural networks for energy-efficient scientific machine learning

arXiv: https://arxiv.org/abs/2412.09379 · HTML: https://mlsanity.com/paper/2412.09379/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 57 references that are in the map.
- First posted on arXiv 12 Dec 2024.

## Builds on (most cited first, 23 of 23)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Principal Neighbourhood Aggregation for Graph Nets](https://mlsanity.com/paper/2004.05718/) (2020)
- [Training Spiking Neural Networks Using Lessons From Deep Learning](https://mlsanity.com/paper/2109.12894/) (2021)
- [Direct Training for Spiking Neural Networks: Faster, Larger, Better](https://mlsanity.com/paper/1809.05793/) (2018)
- [SuperSpike: Supervised learning in multi-layer spiking neural networks](https://mlsanity.com/paper/1705.11146/) (2017)
- [Spiking Deep Networks with LIF Neurons](https://mlsanity.com/paper/1510.08829/) (2015)
- [Graph Neural Networks for Wireless Communications: From Theory to Practice](https://mlsanity.com/paper/2203.10800/) (2022)
- [Graph Neural Networks with Continual Learning for Fake News Detection from Social Media](https://mlsanity.com/paper/2007.03316/) (2020)
- [Event-Based Angular Velocity Regression with Spiking Networks](https://mlsanity.com/paper/2003.02790/) (2020)
- [Direct Training High-Performance Deep Spiking Neural Networks: A Review of Theories and Methods](https://mlsanity.com/paper/2405.04289/) (2024)
- [Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks](https://mlsanity.com/paper/2208.10364/) (2022)
- [Graph Neural Networks for Communication Networks: Context, Use Cases and Opportunities](https://mlsanity.com/paper/2112.14792/) (2021)
- [Graph-based Deep Learning for Communication Networks: A Survey](https://mlsanity.com/paper/2106.02533/) (2021)
- [Neuromorphic Artificial Intelligence Systems](https://mlsanity.com/paper/2205.13037/) (2022)
- [Mapping Spiking Neural Networks to Neuromorphic Hardware](https://mlsanity.com/paper/1909.01843/) (2019)
- [Spiking neural networks for nonlinear regression](https://mlsanity.com/paper/2210.03515/) (2022)
- [Spiking Neural Operators for Scientific Machine Learning](https://mlsanity.com/paper/2205.10130/) (2022)
- [SiGNN: A Spike-induced Graph Neural Network for Dynamic Graph Representation Learning](https://mlsanity.com/paper/2404.07941/) (2024)
- [Artificial to Spiking Neural Networks Conversion for Scientific Machine Learning](https://mlsanity.com/paper/2308.16372/) (2023)
- [Neuroscience inspired scientific machine learning (Part-1): Variable spiking neuron for regression](https://mlsanity.com/paper/2311.09267/) (2023)

## Built on by (most cited first, 3 of 3)

- [Event-driven physics-informed operator learning for reliability analysis](https://mlsanity.com/paper/2511.06083/) (2025)
- [Low-Latency Activation-Regularized Sparse Neural Operators with Distillation Assistance Towards Real-Time Neuromorphic Virtual Sensing](https://mlsanity.com/paper/2608.23987/) (2026)
- [CoNBONet: Conformalized Neuroscience-inspired Bayesian Operator Network for Reliability Analysis](https://mlsanity.com/paper/2603.21678/) (2026)

## Abstract (arXiv)

Graph-based representations for samples of computational mechanics-related datasets can prove instrumental when dealing with problems like irregular domains or molecular structures of materials, etc. To effectively analyze and process such datasets, deep learning offers Graph Neural Networks (GNNs) that utilize techniques like message-passing within their architecture. The issue, however, is that as the individual graph scales and/ or GNN architecture becomes increasingly complex, the increased energy budget of the overall deep learning model makes it unsustainable and restricts its applications in applications like edge computing. To overcome this, we propose in this paper Hybrid Variable Spiking Graph Neural Networks (HVS-GNNs) that utilize Variable Spiking Neurons (VSNs) within their architecture to promote sparse communication and hence reduce the overall energy budget. VSNs, while promoting sparse event-driven computations, also perform well for regression tasks, which are often encountered in computational mechanics applications and are the main target of this paper. Three examples dealing with prediction of mechanical properties of material based on microscale/ mesoscale structures are shown to test the performance of the proposed HVS-GNNs in regression tasks. We have also compared the performance of HVS-GNN architectures with the performance of vanilla GNNs and GNNs utilizing leaky integrate and fire neurons. The results produced show that HVS-GNNs perform well for regression tasks, all while promoting sparse communication and, hence, energy efficiency.