# Adaptive Workload Distribution for Accuracy-aware DNN Inference on Collaborative Edge Platforms

arXiv: https://arxiv.org/abs/2310.10157 · HTML: https://mlsanity.com/paper/2310.10157/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 17 references that are in the map.
- First posted on arXiv 16 Oct 2023.

## Builds on (most cited first, 4 of 4)

- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Online Learning for Orchestration of Inference in Multi-User End-Edge-Cloud Networks](https://mlsanity.com/paper/2202.10541/) (2022)
- [Online Algorithms for Hierarchical Inference in Deep Learning applications at the Edge](https://mlsanity.com/paper/2304.00891/) (2023)
- [Efficient Computer Vision on Edge Devices with Pipeline-Parallel Hierarchical Neural Networks](https://mlsanity.com/paper/2109.13356/) (2021)

## Built on by (most cited first, 1 of 1)

- [HiDP: Hierarchical DNN Partitioning for Distributed Inference on Heterogeneous Edge Platforms](https://mlsanity.com/paper/2411.16086/) (2024)

## Abstract (arXiv)

DNN inference can be accelerated by distributing the workload among a cluster of collaborative edge nodes. Heterogeneity among edge devices and accuracy-performance trade-offs of DNN models present a complex exploration space while catering to the inference performance requirements. In this work, we propose adaptive workload distribution for DNN inference, jointly considering node-level heterogeneity of edge devices, and application-specific accuracy and performance requirements. Our proposed approach combinatorially optimizes heterogeneity-aware workload partitioning and dynamic accuracy configuration of DNN models to ensure performance and accuracy guarantees. We tested our approach on an edge cluster of Odroid XU4, Raspberry Pi4, and Jetson Nano boards and achieved an average gain of 41.52% in performance and 5.2% in output accuracy as compared to state-of-the-art workload distribution strategies.