SlimEdge: Performance and Device Aware Distributed DNN Deployment on Resource-Constrained Edge Hardware

TL;DR

This paper introduces SlimEdge, a framework for deploying distributed DNNs on resource-limited edge devices that optimizes model pruning considering hardware constraints, task accuracy, and device failures, demonstrated on MVCNN for 3D recognition.

Contribution

It presents a novel multi-objective optimization approach integrating structured pruning with failure resilience for distributed DNN deployment on edge hardware.

Findings

Inference time reduced by up to 4.7x

Models meet accuracy and memory bounds under failures

Framework effectively allocates pruning based on view importance

Abstract

Distributed deep neural networks (DNNs) have become central to modern computer vision, yet their deployment on resource-constrained edge devices remains hindered by substantial parameter counts, computational demands, and the probability of device failure. Here, we present an approach to the efficient deployment of distributed DNNs that jointly respect hardware limitations, preserve task performance, and remain robust to partial system failures. Our method integrates structured model pruning with a multi-objective optimization framework to tailor network capacity for heterogeneous device constraints, while explicitly accounting for device availability and failure probability during deployment. We demonstrate this framework using Multi-View Convolutional Neural Networks (MVCNN), a state-of-the-art architecture for 3D object recognition, by quantifying the contribution of individual views to classification accuracy and allocating pruning budgets accordingly. Experimental results show that the resulting models satisfy user-specified bounds on accuracy and memory footprint, even under multiple simultaneous device failures. The inference time is reduced by factors up to 4.7x across diverse simulated device configurations. These findings suggest that performance-aware, view-adaptive, and failure-resilient compression provides a viable pathway for deploying complex vision models in distributed edge environments.