Neuroscience Inspired Graph Operators Towards Edge-Deployable Virtual Sensing for Irregular Geometries

2026-04-17

AI Summary

This work addresses the challenges of accuracy, multiphysics coupling, and energy efficiency in real-time sparse-to-dense virtual sensing for highly irregular engineering systems on edge devices. To this end, we propose the Variable Spiking Graph Neural Operator (VS-GNO), which uniquely integrates spiking neurons with variable firing thresholds into a graph neural operator framework. By combining spectral-spatial graph convolutions with an energy-error joint optimization loss, VS-GNO is tailored for neuromorphic hardware deployment. Experimental results demonstrate that, against a non-spiking L₂ error baseline of 0.4%, the spectral variant of VS-GNO achieves a reconstruction error of 0.71% with an average spiking rate of 15%, while the full model attains 1.04% error at a 24.5% spiking rate. These results significantly reduce energy consumption while preserving reconstruction fidelity, thereby overcoming the performance limitations of existing spiking models in regression tasks.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Learning & Optimization for CV

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Predicting full-field physics through the real-time virtual sensing of engineering systems can enhance limited physical sensors but often requires sparse-to-dense reconstruction, complex multiphysics, and highly irregular geometries as well as strict latency and energy constraints for edge-deployability. Neural operators have been presented as a potential candidate for such applications but few architectures exist that explicitly address power consumption. Spiking neuron integration can provide a potential solution when integrated on neuromorphic hardware but the current existing neuron models result in severe performance degradation towards regression-based virtual sensing. To address the performance concerns and edge-constraints, we present the Variable Spiking Graph Neural Operator (VS-GNO) which integrates a sophisticated spectral-spatial convolutional analysis and a previously developed Variable Spiking Neuron (VSN) and energy-error balance loss function. With a non-spiking $L_2$ error baseline of $0.4\%$, VS-GNO can provide a reconstruction error of $0.71\%$ with $15\%$ average spiking in its spectral-only form and $1.04\%$ with $24.5\%$ spiking in its entire form. These results position VS-GNO as a promising step towards energy-efficient, edge-deployable neural operators for real-time sparse-to-dense virtual sensing in complex, highly irregular engineering environments.

Problem

• virtual sensing
• irregular geometries
• edge-deployable
• neural operators
• spiking neurons

Innovation

• Spiking Neural Operators
• Edge-deployable Virtual Sensing
• Irregular Geometries
• Energy-Efficient AI
• Graph Neural Networks