Edge Intelligence with Spiking Neural Networks

2025-07-18

AI Summary

Constrained edge-device resources, high computational demands of conventional deep learning, and latency, bandwidth, and privacy risks arising from centralized data processing hinder edge intelligence. Method: This paper proposes EdgeSNN, a systematic research framework for spiking neural networks (SNNs) tailored to edge intelligence. It introduces the first taxonomy of edge SNNs, exposes limitations of generic hardware evaluation, and advocates a “model–algorithm–hardware” co-design paradigm integrating event-driven computation, lightweight inference, resource-aware training, and domain-specific hardware acceleration. It also pioneers a dual-track benchmarking strategy. Contribution/Results: EdgeSNN delivers the first comprehensive survey of edge SNN research progress and challenges; establishes an end-to-end technical pathway enabling secure, adaptive edge learning under non-stationary data conditions; and constitutes the field’s inaugural systematic reference framework—explicitly identifying key open problems.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Search and Optimization: Learning to Search

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: Cloud, edge and content delivery systems for the Web
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

The convergence of artificial intelligence and edge computing has spurred growing interest in enabling intelligent services directly on resource-constrained devices. While traditional deep learning models require significant computational resources and centralized data management, the resulting latency, bandwidth consumption, and privacy concerns have exposed critical limitations in cloud-centric paradigms. Brain-inspired computing, particularly Spiking Neural Networks (SNNs), offers a promising alternative by emulating biological neuronal dynamics to achieve low-power, event-driven computation. This survey provides a comprehensive overview of Edge Intelligence based on SNNs (EdgeSNNs), examining their potential to address the challenges of on-device learning, inference, and security in edge scenarios. We present a systematic taxonomy of EdgeSNN foundations, encompassing neuron models, learning algorithms, and supporting hardware platforms. Three representative practical considerations of EdgeSNN are discussed in depth: on-device inference using lightweight SNN models, resource-aware training and updating under non-stationary data conditions, and secure and privacy-preserving issues. Furthermore, we highlight the limitations of evaluating EdgeSNNs on conventional hardware and introduce a dual-track benchmarking strategy to support fair comparisons and hardware-aware optimization. Through this study, we aim to bridge the gap between brain-inspired learning and practical edge deployment, offering insights into current advancements, open challenges, and future research directions. To the best of our knowledge, this is the first dedicated and comprehensive survey on EdgeSNNs, providing an essential reference for researchers and practitioners working at the intersection of neuromorphic computing and edge intelligence.

Problem

• Enable intelligent services on resource-constrained edge devices
• Address latency, bandwidth, and privacy in cloud-centric paradigms
• Explore SNNs for low-power, event-driven edge computation

Innovation

• Edge Intelligence with Spiking Neural Networks
• Low-power event-driven computation for edge devices
• Dual-track benchmarking for hardware-aware optimization