NeuCODEX: Edge-Cloud Co-Inference with Spike-Driven Compression and Dynamic Early-Exit
This work addresses the problem of high latency and energy costs for SNN inference in resource-constrained edge environments, offering a practical solution with incremental improvements over existing co-inference systems.
The paper tackles the challenge of deploying Spiking Neural Networks (SNNs) at the edge by introducing NeuCODEX, an edge-cloud co-inference architecture that reduces data transfer by up to 2048x, cuts edge energy consumption by over 90%, and lowers latency by up to 3x with less than 2% accuracy drop.
Spiking Neural Networks (SNNs) offer significant potential for enabling energy-efficient intelligence at the edge. However, performing full SNN inference at the edge can be challenging due to the latency and energy constraints arising from fixed and high timestep overheads. Edge-cloud co-inference systems present a promising solution, but their deployment is often hindered by high latency and feature transmission costs. To address these issues, we introduce NeuCODEX, a neuromorphic co-inference architecture that jointly optimizes both spatial and temporal redundancy. NeuCODEX incorporates a learned spike-driven compression module to reduce data transmission and employs a dynamic early-exit mechanism to adaptively terminate inference based on output confidence. We evaluated NeuCODEX on both static images (CIFAR10 and Caltech) and neuromorphic event streams (CIFAR10-DVS and N-Caltech). To demonstrate practicality, we prototyped NeuCODEX on ResNet-18 and VGG-16 backbones in a real edge-to-cloud testbed. Our proposed system reduces data transfer by up to 2048x and edge energy consumption by over 90%, while reducing end-to-end latency by up to 3x compared to edge-only inference, all with a negligible accuracy drop of less than 2%. In doing so, NeuCODEX enables practical, high-performance SNN deployment in resource-constrained environments.