mlsanityData to 7 Oct 2026

A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques

arXiv 2302.08571 ↗First posted 16 Feb 2023cs.LG cs.AI cs.DCcited by 4

Not on the map. Why?

Abstract (arXiv)

The union of Edge Computing (EC) and Artificial Intelligence (AI) has brought forward the Edge AI concept to provide intelligent solutions close to the end-user environment, for privacy preservation, low latency to real-time performance, and resource optimization. Machine Learning (ML), as the most advanced branch of AI in the past few years, has shown encouraging results and applications in the edge environment. Nevertheless, edge-powered ML solutions are more complex to realize due to the joint constraints from both edge computing and AI domains, and the corresponding solutions are expected to be efficient and adapted in technologies such as data processing, model compression, distributed inference, and advanced learning paradigms for Edge ML requirements. Despite the fact that a great deal of the attention garnered by Edge ML is gained in both the academic and industrial communities, we noticed the lack of a complete survey on existing Edge ML technologies to provide a common understanding of this concept. To tackle this, this paper aims at providing a comprehensive taxonomy and a systematic review of Edge ML techniques, focusing on the soft computing aspects of existing paradigms and techniques. We start by identifying the Edge ML requirements driven by the joint constraints. We then extensively survey more than twenty paradigms and techniques along with their representative work, covering two main parts: edge inference, and edge learning. In particular, we analyze how each technique fits into Edge ML by meeting a subset of the identified requirements. We also summarize Edge ML frameworks and open issues to shed light on future directions for Edge ML.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 140 of its 274 references that are in the map. First posted on arXiv 16 Feb 2023.

Builds on

140 of 274 references.

References · 140

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  5. 2020Language Models are Few-Shot Learnerscited by 32,199
  6. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  8. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  9. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  10. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  11. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  12. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
38 more
  1. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  2. 2016Densely Connected Convolutional Networkscited by 6,691
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  6. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  7. 2014Going Deeper with Convolutionscited by 4,231
  8. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  9. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  10. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  11. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  12. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  13. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  14. 2019Searching for MobileNetV3cited by 1,984
  15. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  16. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  17. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  18. 2019Contrastive Multiview Codingcited by 1,297
  19. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  20. 2023SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shotcited by 1,090
  21. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  22. 2019When Does Label Smoothing Help?cited by 985
  23. 2018Neural Network Acceptability Judgmentscited by 952
  24. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  25. 2017A Survey on Multi-Task Learningcited by 838
  26. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  27. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  28. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 741
  29. 2022data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Languagecited by 718
  30. 2019A Closer Look at Few-shot Classificationcited by 679
  31. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 656
  32. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  33. 2021Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LMcited by 621
  34. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 591
  35. 2022Open-Vocabulary Semantic Segmentation with Mask-adapted CLIPcited by 560
  36. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  37. 2019Meta-Learning with Implicit Gradientscited by 523
  38. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475

50 most cited of 140 All 140 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 1.

4 papers.

  1. 2024Training Machine Learning models at the Edge: A Surveycited by 11
  2. 2024AccidentGPT: Large Multi-Modal Foundation Model for Traffic Accident Analysiscited by 10
  3. 2025Achieving Trustworthy Real-Time Decision Support Systems with Low-Latency Interpretable AI Modelscited by 1
  4. 2026TsetlinWiSARD: On-Chip Training of Weightless Neural Networks using Tsetlin Automata on FPGAscited by 0