# DistrEdge: Speeding up Convolutional Neural Network Inference on Distributed Edge Devices

arXiv: https://arxiv.org/abs/2202.01699 · HTML: https://mlsanity.com/paper/2202.01699/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Feb 2022.

## Built on by (most cited first, 8 of 8)

- [Map-and-Conquer: Energy-Efficient Mapping of Dynamic Neural Nets onto Heterogeneous MPSoCs](https://mlsanity.com/paper/2302.12926/) (2023)
- [Efficient Partitioning Vision Transformer on Edge Devices for Distributed Inference](https://mlsanity.com/paper/2410.11650/) (2024)
- [Learning the Optimal Path and DNN Partition for Collaborative Edge Inference](https://mlsanity.com/paper/2410.01857/) (2024)
- [A Performance Analysis of You Only Look Once Models for Deployment on Constrained Computational Edge Devices in Drone Applications](https://mlsanity.com/paper/2502.15737/) (2025)
- [DISCO: Distributed Inference with Sparse Communications](https://mlsanity.com/paper/2302.11180/) (2023)
- [Synergy: Towards On-Body AI via Tiny AI Accelerator Collaboration on Wearables](https://mlsanity.com/paper/2401.08637/) (2023)
- [AutoSculpt: A Pattern-based Model Auto-pruning Framework Using Reinforcement Learning and Graph Learning](https://mlsanity.com/paper/2412.18091/) (2024)
- [MANE: A Multi-Path Adaptive Network for Edge Onloading of Deep Neural Networks](https://mlsanity.com/paper/2609.14660/) (2026)

## Abstract (arXiv)

As the number of edge devices with computing resources (e.g., embedded GPUs, mobile phones, and laptops) increases, recent studies demonstrate that it can be beneficial to collaboratively run convolutional neural network (CNN) inference on more than one edge device. However, these studies make strong assumptions on the devices' conditions, and their application is far from practical. In this work, we propose a general method, called DistrEdge, to provide CNN inference distribution strategies in environments with multiple IoT edge devices. By addressing heterogeneity in devices, network conditions, and nonlinear characters of CNN computation, DistrEdge is adaptive to a wide range of cases (e.g., with different network conditions, various device types) using deep reinforcement learning technology. We utilize the latest embedded AI computing devices (e.g., NVIDIA Jetson products) to construct cases of heterogeneous devices' types in the experiment. Based on our evaluations, DistrEdge can properly adjust the distribution strategy according to the devices' computing characters and the network conditions. It achieves 1.1 to 3x speedup compared to state-of-the-art methods.