# Distributed Deep Learning Inference Acceleration using Seamless Collaboration in Edge Computing

arXiv: https://arxiv.org/abs/2207.11294 · HTML: https://mlsanity.com/paper/2207.11294/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Early exit and edge inference, one of 12 directions in Efficient LLM inference and serving.
- Builds on 2 of its 12 references that are in the map.
- First posted on arXiv 22 Jul 2022.

## Placed in

- Efficient LLM inference and serving / [Early exit and edge inference](https://mlsanity.com/inference/early-exit-and-edge-inference/)

## Builds on (most cited first, 2 of 2)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)

## Built on by (most cited first, 4 of 4)

- [Efficient High-Resolution Deep Learning: A Survey](https://mlsanity.com/paper/2207.13050/) (2022)
- [Graph Reinforcement Learning-based CNN Inference Offloading in Dynamic Edge Computing](https://mlsanity.com/paper/2210.13464/) (2022)
- [Design and Prototyping Distributed CNN Inference Acceleration in Edge Computing](https://mlsanity.com/paper/2211.13778/) (2022)
- [Beyond Imaging: Vision Transformer Digital Twin Surrogates for 3D+T Biological Tissue Dynamics](https://mlsanity.com/paper/2508.15883/) (2025)

## Abstract (arXiv)

This paper studies inference acceleration using distributed convolutional neural networks (CNNs) in collaborative edge computing. To ensure inference accuracy in inference task partitioning, we consider the receptive-field when performing segment-based partitioning. To maximize the parallelization between the communication and computing processes, thereby minimizing the total inference time of an inference task, we design a novel task collaboration scheme in which the overlapping zone of the sub-tasks on secondary edge servers (ESs) is executed on the host ES, named as HALP. We further extend HALP to the scenario of multiple tasks. Experimental results show that HALP can accelerate CNN inference in VGG-16 by 1.7-2.0x for a single task and 1.7-1.8x for 4 tasks per batch on GTX 1080TI and JETSON AGX Xavier, which outperforms the state-of-the-art work MoDNN. Moreover, we evaluate the service reliability under time-variant channel, which shows that HALP is an effective solution to ensure high service reliability with strict service deadline.