# Dynamic Split Computing for Efficient Deep Edge Intelligence

arXiv: https://arxiv.org/abs/2205.11269 · HTML: https://mlsanity.com/paper/2205.11269/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 32 references that are in the map.
- First posted on arXiv 23 May 2022.

## Builds on (most cited first, 19 of 19)

- [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)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Adaptive Computation Time for Recurrent Neural Networks](https://mlsanity.com/paper/1603.08983/) (2016)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [PonderNet: Learning to Ponder](https://mlsanity.com/paper/2107.05407/) (2021)
- [Dynamic Channel Pruning: Feature Boosting and Suppression](https://mlsanity.com/paper/1810.05331/) (2018)
- [Convergence of Edge Computing and Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/1907.08349/) (2019)
- [Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges](https://mlsanity.com/paper/2103.04505/) (2021)
- [Why should we add early exits to neural networks?](https://mlsanity.com/paper/2004.12814/) (2020)
- [Multi-Exit Vision Transformer for Dynamic Inference](https://mlsanity.com/paper/2106.15183/) (2021)

## Built on by (most cited first, 18 of 18)

- [FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing](https://mlsanity.com/paper/2302.10681/) (2023)
- [Efficient High-Resolution Deep Learning: A Survey](https://mlsanity.com/paper/2207.13050/) (2022)
- [Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge Computing](https://mlsanity.com/paper/2212.11751/) (2022)
- [Efficient Partitioning Vision Transformer on Edge Devices for Distributed Inference](https://mlsanity.com/paper/2410.11650/) (2024)
- [Semantic Edge Computing and Semantic Communications in 6G Networks: A Unifying Survey and Research Challenges](https://mlsanity.com/paper/2411.18199/) (2024)
- [Dynamic Semantic Compression for CNN Inference in Multi-access Edge Computing: A Graph Reinforcement Learning-based Autoencoder](https://mlsanity.com/paper/2401.12167/) (2024)
- [Memory- and Latency-Constrained Inference of Large Language Models via Adaptive Split Computing](https://mlsanity.com/paper/2511.04002/) (2025)
- [Input Conditioned Layer Dropping in Speech Foundation Models](https://mlsanity.com/paper/2507.07954/) (2025)
- [PRISM: Distributed Inference for Foundation Models at Edge](https://mlsanity.com/paper/2507.12145/) (2025)
- [Cooperative Inference for Real-Time 3D Human Pose Estimation in Multi-Device Edge Networks](https://mlsanity.com/paper/2504.03052/) (2025)
- [Why Should the Server Do It All?: A Scalable, Versatile, and Model-Agnostic Framework for Server-Light DNN Inference over Massively Distributed Clients via Training-Free Intermediate Feature Compression](https://mlsanity.com/paper/2511.11608/) (2025)
- [Design and Prototyping Distributed CNN Inference Acceleration in Edge Computing](https://mlsanity.com/paper/2211.13778/) (2022)
- [Communication-Aware Consistent Edge Selection for Mobile Users and Autonomous Vehicles](https://mlsanity.com/paper/2408.03435/) (2024)
- [ReinDSplit: Reinforced Dynamic Split Learning for Pest Recognition in Precision Agriculture](https://mlsanity.com/paper/2506.13935/) (2025)
- [Range Asymmetric Numeral Systems-Based Lightweight Intermediate Feature Compression for Split Computing of Deep Neural Networks](https://mlsanity.com/paper/2511.11664/) (2025)
- [Quantization in Federated Learning: Methods, Challenges and Future Directions](https://mlsanity.com/paper/2606.26822/) (2026)
- [MANE: A Multi-Path Adaptive Network for Edge Onloading of Deep Neural Networks](https://mlsanity.com/paper/2609.14660/) (2026)
- [FRESHLATENT: Channel-Aware Latent Adaptation for Resource-Constrained Embodied VLM Perception](https://mlsanity.com/paper/2609.30629/) (2026)

## Abstract (arXiv)

Deploying deep neural networks (DNNs) on IoT and mobile devices is a challenging task due to their limited computational resources. Thus, demanding tasks are often entirely offloaded to edge servers which can accelerate inference, however, it also causes communication cost and evokes privacy concerns. In addition, this approach leaves the computational capacity of end devices unused. Split computing is a paradigm where a DNN is split into two sections; the first section is executed on the end device, and the output is transmitted to the edge server where the final section is executed. Here, we introduce dynamic split computing, where the optimal split location is dynamically selected based on the state of the communication channel. By using natural bottlenecks that already exist in modern DNN architectures, dynamic split computing avoids retraining and hyperparameter optimization, and does not have any negative impact on the final accuracy of DNNs. Through extensive experiments, we show that dynamic split computing achieves faster inference in edge computing environments where the data rate and server load vary over time.