mlsanityData to 7 Oct 2026

Auto-Split: A General Framework of Collaborative Edge-Cloud AI

arXiv 2108.13041 ↗First posted 30 Aug 2021cs.LG cs.AIcited by 29

Not on the map. Why?

Abstract (arXiv)

In many industry scale applications, large and resource consuming machine learning models reside in powerful cloud servers. At the same time, large amounts of input data are collected at the edge of cloud. The inference results are also communicated to users or passed to downstream tasks at the edge. The edge often consists of a large number of low-power devices. It is a big challenge to design industry products to support sophisticated deep model deployment and conduct model inference in an efficient manner so that the model accuracy remains high and the end-to-end latency is kept low. This paper describes the techniques and engineering practice behind Auto-Split, an edge-cloud collaborative prototype of Huawei Cloud. This patented technology is already validated on selected applications, is on its way for broader systematic edge-cloud application integration, and is being made available for public use as an automated pipeline service for end-to-end cloud-edge collaborative intelligence deployment. To the best of our knowledge, there is no existing industry product that provides the capability of Deep Neural Network (DNN) splitting.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 38 of its 59 references that are in the map. First posted on arXiv 30 Aug 2021.

Builds on

38 of 59 references.

References · 38

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  4. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  5. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  6. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  7. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  8. 2019Learned Step Size Quantizationcited by 604
  9. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 591
  10. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  11. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  12. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 456
26 more
  1. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 426
  2. 2019HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precisioncited by 387
  3. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 332
  4. 2017A Survey of Model Compression and Acceleration for Deep Neural Networkscited by 298
  5. 2018Model compression via distillation and quantizationcited by 287
  6. 2018LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networkscited by 272
  7. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 265
  8. 2019Low-bit Quantization of Neural Networks for Efficient Inferencecited by 185
  9. 2019Improving Neural Network Quantization without Retraining using Outlier Channel Splittingcited by 150
  10. 2019Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computingcited by 150
  11. 2018NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applicationscited by 146
  12. 2018Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Searchcited by 122
  13. 2020SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloudcited by 109
  14. 2017Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracycited by 100
  15. 2019Loss Aware Post-training Quantizationcited by 94
  16. 2018ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptationcited by 76
  17. 2018Post-training 4-bit quantization of convolution networks for rapid-deploymentcited by 38
  18. 2019PULP-NN: Accelerating Quantized Neural Networks on Parallel Ultra-Low-Power RISC-V Processorscited by 34
  19. 2019Memory-Driven Mixed Low Precision Quantization For Enabling Deep Network Inference On Microcontrollerscited by 31
  20. 2019PREMA: A Predictive Multi-task Scheduling Algorithm For Preemptible Neural Processing Unitscited by 30
  21. 2018Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloudcited by 28
  22. 2018SCALE-Sim: Systolic CNN Accelerator Simulatorcited by 26
  23. 2019SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Modelscited by 22
  24. 2017Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectorscited by 12
  25. 2019Neural Network Distiller: A Python Package For DNN Compression Researchcited by 12
  26. 2018Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Maskingcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 7; 2023: 4; 2024: 7; 2025: 7; 2026: 3.

29 papers.

Sort:

By area:

  1. 2021Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AIcited by 38
  2. 2022SC2 Benchmark: Supervised Compression for Split Computingcited by 14
  3. 2025Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Surveycited by 13
  4. 2023Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Informationcited by 11
  5. 2022Device-Cloud Collaborative Recommendation via Meta Controllercited by 10
  6. 2022E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Modelscited by 8
  7. 2022Privacy-Preserving Visual Localization with Event Camerascited by 6
  8. 2022TinyMLOps: Operational Challenges for Widespread Edge AI Adoptioncited by 3
  9. 2022Measuring and Controlling Split Layer Privacy Leakage Using Fisher Informationcited by 3
  10. 2023Salted Inference: Enhancing Privacy while Maintaining Efficiency of Split Inference in Mobile Computingcited by 3
  11. 2024DIET: Customized Slimming for Incompatible Networks in Sequential Recommendationcited by 3
  12. 2024A Scene-aware Models Adaptation Scheme for Cross-scene Online Inference on Mobile Devicescited by 3
17 more
  1. 2025A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT Networkscited by 3
  2. 2024Socialized Learning: A Survey of the Paradigm Shift for Edge Intelligence in Networked Systemscited by 2
  3. 2025Efficient Distributed Retrieval-Augmented Generation for Enhancing Language Model Performancecited by 2
  4. 2023Synergy: Towards On-Body AI via Tiny AI Accelerator Collaboration on Wearablescited by 1
  5. 2024On the Impact of White-box Deployment Strategies for Edge AI on Latency and Model Performancecited by 1
  6. 2025MEL: Multi-level Ensemble Learning for Resource-Constrained Environmentscited by 1
  7. 2025Intra-DP: A High Performance Collaborative Inference System for Mobile Edge Computingcited by 1
  8. 2022Fault-Tolerant Collaborative Inference through the Edge-PRUNE Frameworkcited by 0
  9. 2023Towards A Flexible Accuracy-Oriented Deep Learning Module Inference Latency Prediction Framework for Adaptive Optimization Algorithmscited by 0
  10. 2024Edge AI as a Service with Coordinated Deep Neural Networkscited by 0
  11. 2024Optimal In-Network Distribution of Learning Functions for a Secure-by-Design Programmable Data Plane of Next-Generation Networkscited by 0
  12. 2024Distributed Collaborative Inference System in Next-Generation Networks and Communicationcited by 0
  13. 2025Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimizationcited by 0
  14. 2025CoLM: Collaborative Large Models via A Client-Server Paradigmcited by 0
  15. 2026Trainable Bitwise Soft Quantization for Input Feature Compressioncited by 0
  16. 2026AdaDINO: Context-Adaptive DINO-Distilled Vision Foundation Models for Efficient Open-Vocabulary Edge Inferencecited by 0
  17. 2026Parameter- and Bandwidth-Efficient Edge--cloud Many-to-Many Speech-to-Text Translationcited by 0