# Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges

arXiv: https://arxiv.org/abs/2103.04505 · HTML: https://mlsanity.com/paper/2103.04505/

## Key facts

- Cited by 115 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 87 of its 183 references that are in the map.
- First posted on arXiv 8 Mar 2021.

## 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, 30 of 87)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)

## Built on by (most cited first, 30 of 115)

- [Mobile Edge Intelligence for Large Language Models: A Contemporary Survey](https://mlsanity.com/paper/2407.18921/) (2024)
- [Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions](https://mlsanity.com/paper/2106.05022/) (2021)
- [Privacy and Efficiency of Communications in Federated Split Learning](https://mlsanity.com/paper/2301.01824/) (2023)
- [Dynamic Split Computing for Efficient Deep Edge Intelligence](https://mlsanity.com/paper/2205.11269/) (2022)
- [Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicity](https://mlsanity.com/paper/2306.02652/) (2023)
- [SC2 Benchmark: Supervised Compression for Split Computing](https://mlsanity.com/paper/2203.08875/) (2022)
- [SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems](https://mlsanity.com/paper/2204.04705/) (2022)
- [Adaptive Semantic Token Communication for Transformer-based Edge Inference](https://mlsanity.com/paper/2505.17604/) (2025)
- [SplitEE: Early Exit in Deep Neural Networks with Split Computing](https://mlsanity.com/paper/2309.09195/) (2023)
- [FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing](https://mlsanity.com/paper/2302.10681/) (2023)
- [Binarizing Split Learning for Data Privacy Enhancement and Computation Reduction](https://mlsanity.com/paper/2206.04864/) (2022)
- [Resource-Constrained Edge AI with Early Exit Prediction](https://mlsanity.com/paper/2206.07269/) (2022)
- [Conditional computation in neural networks: principles and research trends](https://mlsanity.com/paper/2403.07965/) (2024)
- [Towards Understanding How Knowledge Evolves in Large Vision-Language Models](https://mlsanity.com/paper/2504.02862/) (2025)
- [Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques](https://mlsanity.com/paper/2112.15131/) (2021)
- [Efficient High-Resolution Deep Learning: A Survey](https://mlsanity.com/paper/2207.13050/) (2022)
- [I-SplitEE: Image classification in Split Computing DNNs with Early Exits](https://mlsanity.com/paper/2401.10541/) (2024)
- [Privacy Vulnerability of Split Computing to Data-Free Model Inversion Attacks](https://mlsanity.com/paper/2107.06304/) (2021)
- [I-SPLIT: Deep Network Interpretability for Split Computing](https://mlsanity.com/paper/2209.11607/) (2022)
- [Energy Consumption of Neural Networks on NVIDIA Edge Boards: an Empirical Model](https://mlsanity.com/paper/2210.01625/) (2022)
- [Update Compression for Deep Neural Networks on the Edge](https://mlsanity.com/paper/2203.04516/) (2022)
- [Lambda-Split: A Privacy-Preserving Split Computing Framework for Cloud-Powered Generative AI](https://mlsanity.com/paper/2310.14651/) (2023)
- [FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression](https://mlsanity.com/paper/2403.16677/) (2024)
- [A Multi-task Supervised Compression Model for Split Computing](https://mlsanity.com/paper/2501.01420/) (2025)
- [Cross-layer Attention Sharing for Pre-trained Large Language Models](https://mlsanity.com/paper/2408.01890/) (2024)
- [Semantic Edge Computing and Semantic Communications in 6G Networks: A Unifying Survey and Research Challenges](https://mlsanity.com/paper/2411.18199/) (2024)
- [Unlocking Visual Secrets: Inverting Features with Diffusion Priors for Image Reconstruction](https://mlsanity.com/paper/2412.10448/) (2024)
- [A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion](https://mlsanity.com/paper/2501.07451/) (2025)
- [DSD: A Distributed Speculative Decoding Solution for Edge-Cloud Agile Large Model Serving](https://mlsanity.com/paper/2511.21669/) (2025)
- [Dynamic Semantic Compression for CNN Inference in Multi-access Edge Computing: A Graph Reinforcement Learning-based Autoencoder](https://mlsanity.com/paper/2401.12167/) (2024)

## Abstract (arXiv)

Mobile devices such as smartphones and autonomous vehicles increasingly rely on deep neural networks (DNNs) to execute complex inference tasks such as image classification and speech recognition, among others. However, continuously executing the entire DNN on mobile devices can quickly deplete their battery. Although task offloading to cloud/edge servers may decrease the mobile device's computational burden, erratic patterns in channel quality, network, and edge server load can lead to a significant delay in task execution. Recently, approaches based on split computing (SC) have been proposed, where the DNN is split into a head and a tail model, executed respectively on the mobile device and on the edge server. Ultimately, this may reduce bandwidth usage as well as energy consumption. Another approach, called early exiting (EE), trains models to embed multiple "exits" earlier in the architecture, each providing increasingly higher target accuracy. Therefore, the trade-off between accuracy and delay can be tuned according to the current conditions or application demands. In this paper, we provide a comprehensive survey of the state of the art in SC and EE strategies by presenting a comparison of the most relevant approaches. We conclude the paper by providing a set of compelling research challenges.