mlsanityData to 14 Oct 2026

Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI

arXiv 2111.06061 ↗First posted 11 Nov 2021cs.LG cs.AIcited by 39

Not on the map. Why?

Abstract (arXiv)

Influenced by the great success of deep learning via cloud computing and the rapid development of edge chips, research in artificial intelligence (AI) has shifted to both of the computing paradigms, i.e., cloud computing and edge computing. In recent years, we have witnessed significant progress in developing more advanced AI models on cloud servers that surpass traditional deep learning models owing to model innovations (e.g., Transformers, Pretrained families), explosion of training data and soaring computing capabilities. However, edge computing, especially edge and cloud collaborative computing, are still in its infancy to announce their success due to the resource-constrained IoT scenarios with very limited algorithms deployed. In this survey, we conduct a systematic review for both cloud and edge AI. Specifically, we are the first to set up the collaborative learning mechanism for cloud and edge modeling with a thorough review of the architectures that enable such mechanism. We also discuss potentials and practical experiences of some on-going advanced edge AI topics including pretraining models, graph neural networks and reinforcement learning. Finally, we discuss the promising directions and challenges in this field.

Key facts. Cited by 39 papers in the map (data through 14 Oct 2026). Builds on 231 of its 400 references that are in the map. First posted on arXiv 11 Nov 2021.

Builds on

231 of 400 references.

References · 231

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  6. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  7. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  8. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  9. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  10. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  11. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  12. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
38 more
  1. 2017Squeeze-and-Excitation Networkscited by 4,789
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  3. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  4. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  5. 2014Going Deeper with Convolutionscited by 4,241
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  7. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  8. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  9. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  10. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  11. 2019Advances and Open Problems in Federated Learningcited by 3,046
  12. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  13. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  14. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  15. 2015VQA: Visual Question Answeringcited by 2,506
  16. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  17. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  18. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  19. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  20. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,868
  21. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  22. 2014FitNets: Hints for Thin Deep Netscited by 1,653
  23. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,631
  24. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  25. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  26. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  27. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  28. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  29. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
  30. 2018Self-Attentive Sequential Recommendationcited by 1,184
  31. 2019TinyBERT: Distilling BERT for Natural Language Understandingcited by 1,167
  32. 2017Mixed Precision Trainingcited by 1,156
  33. 2017Neural Collaborative Filteringcited by 1,111
  34. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  35. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,077
  36. 2019Deep Leakage from Gradientscited by 1,021
  37. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  38. 2021Transformers in Vision: A Surveycited by 1,013

50 most cited of 231 All 231 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 9; 2023: 6; 2024: 14; 2025: 9; 2026: 1.

39 papers.

Sort:

By area:

  1. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 89
  2. 2023Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directionscited by 55
  3. 2022DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalizationcited by 35
  4. 2022A Comprehensive Survey on Trustworthy Recommender Systemscited by 32
  5. 2024PocketLLM: Enabling On-Device Fine-Tuning for Personalized LLMscited by 18
  6. 2022FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregationcited by 16
  7. 2025Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Surveycited by 14
  8. 2024Federated Learning with Bilateral Curation for Partially Class-Disjoint Datacited by 13
  9. 2025Evolution of AI in Education: Agentic Workflowscited by 13
  10. 2024Exploring Training on Heterogeneous Data with Mixture of Low-rank Adapterscited by 12
  11. 2022Intelligent Request Strategy Design in Recommender Systemcited by 10
  12. 2022Device-Cloud Collaborative Recommendation via Meta Controllercited by 10
27 more
  1. 2024Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Surveycited by 10
  2. 2023An Overview on Generative AI at Scale with Edge-Cloud Computingcited by 9
  3. 2024Accelerating End-Cloud Collaborative Inference via Near Bubble-free Pipeline Optimizationcited by 7
  4. 2022NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimensioncited by 5
  5. 2024Reprogramming Distillation for Medical Foundation Modelscited by 5
  6. 2025MST-Distill: Mixture of Specialized Teachers for Cross-Modal Knowledge Distillationcited by 5
  7. 2023Combating Exacerbated Heterogeneity for Robust Models in Federated Learningcited by 4
  8. 2024Federated Learning under Partially Class-Disjoint Data via Manifold Reshapingcited by 4
  9. 2022Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Samplingcited by 3
  10. 2024DIET: Customized Slimming for Incompatible Networks in Sequential Recommendationcited by 3
  11. 2025Forward Once for All: Structural Parameterized Adaptation for Efficient Cloud-coordinated On-device Recommendationcited by 3
  12. 2025A Satellite-Ground Synergistic Large Vision-Language Model System for Earth Observationcited by 3
  13. 2025A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT Networkscited by 3
  14. 2023ECAvg: An Edge-Cloud Collaborative Learning Approach using Averaged Weightscited by 2
  15. 2024Resource Allocation and Workload Scheduling for Large-Scale Distributed Deep Learning: A Surveycited by 2
  16. 2025Edge Intelligence with Spiking Neural Networkscited by 2
  17. 2022A Novel Architecture Slimming Method for Network Pruning and Knowledge Distillationcited by 1
  18. 2023On Achieving Privacy-Preserving State-of-the-Art Edge Intelligencecited by 1
  19. 2023ECLM: Efficient Edge-Cloud Collaborative Learning with Continuous Environment Adaptationcited by 1
  20. 2024Hierarchical Reinforcement Learning for Temporal Abstraction of Listwise Recommendationcited by 1
  21. 2024Towards Real-world Deployment of NILM Systems: Challenges and Practicescited by 1
  22. 2024Distributed Collaborative Inference System in Next-Generation Networks and Communicationcited by 1
  23. 2025Achieving Trustworthy Real-Time Decision Support Systems with Low-Latency Interpretable AI Modelscited by 1
  24. 2025CoFormer: Collaborating with Heterogeneous Edge Devices for Scalable Transformer Inferencecited by 1
  25. 2024End-Cloud Collaboration Framework for Advanced AI Customer Service in E-commercecited by 0
  26. 2024FusedInf: Efficient Swapping of DNN Models for On-Demand Serverless Inference Services on the Edgecited by 0
  27. 2026Deep Reprogramming Distillation for Medical Foundation Modelscited by 0