# Dynamic DNN Decomposition for Lossless Synergistic Inference

arXiv: https://arxiv.org/abs/2101.05952 · HTML: https://mlsanity.com/paper/2101.05952/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 36 references that are in the map.
- First posted on arXiv 15 Jan 2021.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing](https://mlsanity.com/paper/1905.10083/) (2019)
- [Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing](https://mlsanity.com/paper/1910.05316/) (2019)
- [Dual Learning for Machine Translation](https://mlsanity.com/paper/1611.00179/) (2016)
- [Distributed Deep Neural Networks over the Cloud, the Edge and End Devices](https://mlsanity.com/paper/1709.01921/) (2017)
- [Convergence of Edge Computing and Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/1907.08349/) (2019)
- [SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud](https://mlsanity.com/paper/2008.06402/) (2020)
- [Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers](https://mlsanity.com/paper/1809.03137/) (2018)
- [Neural Network Inference on Mobile SoCs](https://mlsanity.com/paper/1908.11450/) (2019)

## Built on by (most cited first, 3 of 3)

- [Semantic Edge Computing and Semantic Communications in 6G Networks: A Unifying Survey and Research Challenges](https://mlsanity.com/paper/2411.18199/) (2024)
- [Moirai: Towards Optimal Placement for Distributed Inference on Heterogeneous Devices](https://mlsanity.com/paper/2312.04025/) (2023)
- [Fault-Tolerant Collaborative Inference through the Edge-PRUNE Framework](https://mlsanity.com/paper/2206.08152/) (2022)

## Abstract (arXiv)

Deep neural networks (DNNs) sustain high performance in today's data processing applications. DNN inference is resource-intensive thus is difficult to fit into a mobile device. An alternative is to offload the DNN inference to a cloud server. However, such an approach requires heavy raw data transmission between the mobile device and the cloud server, which is not suitable for mission-critical and privacy-sensitive applications such as autopilot. To solve this problem, recent advances unleash DNN services using the edge computing paradigm. The existing approaches split a DNN into two parts and deploy the two partitions to computation nodes at two edge computing tiers. Nonetheless, these methods overlook collaborative device-edge-cloud computation resources. Besides, previous algorithms demand the whole DNN re-partitioning to adapt to computation resource changes and network dynamics. Moreover, for resource-demanding convolutional layers, prior works do not give a parallel processing strategy without loss of accuracy at the edge side. To tackle these issues, we propose D3, a dynamic DNN decomposition system for synergistic inference without precision loss. The proposed system introduces a heuristic algorithm named horizontal partition algorithm to split a DNN into three parts. The algorithm can partially adjust the partitions at run time according to processing time and network conditions. At the edge side, a vertical separation module separates feature maps into tiles that can be independently run on different edge nodes in parallel. Extensive quantitative evaluation of five popular DNNs illustrates that D3 outperforms the state-of-the-art counterparts up to 3.4 times in end-to-end DNN inference time and reduces backbone network communication overhead up to 3.68 times.