# HiDP: Hierarchical DNN Partitioning for Distributed Inference on Heterogeneous Edge Platforms

arXiv: https://arxiv.org/abs/2411.16086 · HTML: https://mlsanity.com/paper/2411.16086/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 26 references that are in the map.
- First posted on arXiv 25 Nov 2024.

## Builds on (most cited first, 5 of 5)

- [CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devices](https://mlsanity.com/paper/2012.03257/) (2020)
- [High-Throughput CNN Inference on Embedded ARM big.LITTLE Multi-Core Processors](https://mlsanity.com/paper/1903.05898/) (2019)
- [OmniBoost: Boosting Throughput of Heterogeneous Embedded Devices under Multi-DNN Workload](https://mlsanity.com/paper/2307.03290/) (2023)
- [I-SPLIT: Deep Network Interpretability for Split Computing](https://mlsanity.com/paper/2209.11607/) (2022)
- [Adaptive Workload Distribution for Accuracy-aware DNN Inference on Collaborative Edge Platforms](https://mlsanity.com/paper/2310.10157/) (2023)

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

- [Onboard Optimization and Learning: A Survey](https://mlsanity.com/paper/2505.08793/) (2025)
- [CarbonEdge: Carbon-Aware Deep Learning Inference Framework for Sustainable Edge Computing](https://mlsanity.com/paper/2603.27420/) (2026)
- [CanniUplift: A Holistic Framework for Mitigating Seller and Incentive Cannibalization in E-commerce Uplift Modeling](https://mlsanity.com/paper/2607.05242/) (2026)
- [Efficient Block-Layer Parallel Inference for Vision-Language-Action on Hybrid Architectures](https://mlsanity.com/paper/2608.14586/) (2026)

## Abstract (arXiv)

Edge inference techniques partition and distribute Deep Neural Network (DNN) inference tasks among multiple edge nodes for low latency inference, without considering the core-level heterogeneity of edge nodes. Further, default DNN inference frameworks also do not fully utilize the resources of heterogeneous edge nodes, resulting in higher inference latency. In this work, we propose a hierarchical DNN partitioning strategy (HiDP) for distributed inference on heterogeneous edge nodes. Our strategy hierarchically partitions DNN workloads at both global and local levels by considering the core-level heterogeneity of edge nodes. We evaluated our proposed HiDP strategy against relevant distributed inference techniques over widely used DNN models on commercial edge devices. On average our strategy achieved 38% lower latency, 46% lower energy, and 56% higher throughput in comparison with other relevant approaches.