mlsanityData to 14 Oct 2026

TinyMLOps: Operational Challenges for Widespread Edge AI Adoption

arXiv 2203.10923 ↗First posted 21 Mar 2022cs.LG cs.DC cs.NEcited by 3

Not on the map. Why?

Abstract (arXiv)

Deploying machine learning applications on edge devices can bring clear benefits such as improved reliability, latency and privacy but it also introduces its own set of challenges. Most works focus on the limited computational resources of edge platforms but this is not the only bottleneck standing in the way of widespread adoption. In this paper we list several other challenges that a TinyML practitioner might need to consider when operationalizing an application on edge devices. We focus on tasks such as monitoring and managing the application, common functionality for a MLOps platform, and show how they are complicated by the distributed nature of edge deployment. We also discuss issues that are unique to edge applications such as protecting a model's intellectual property and verifying its integrity.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 41 of its 83 references that are in the map. First posted on arXiv 21 Mar 2022.

Builds on

41 of 83 references.

References · 41

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  3. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  4. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  5. 2019Towards Federated Learning at Scale: System Designcited by 832
  6. 2016Stealing Machine Learning Models via Prediction APIscited by 619
  7. 2021A White Paper on Neural Network Quantizationcited by 472
  8. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 434
  9. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
  10. 2021Federated Learning on Non-IID Data: A Surveycited by 346
  11. 2018PRADA: Protecting against DNN Model Stealing Attackscited by 165
  12. 2020Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Datacited by 125
29 more
  1. 2020Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learningcited by 112
  2. 2018Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardwarecited by 102
  3. 2019Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregationcited by 100
  4. 2018Snapshot Distillation: Teacher-Student Optimization in One Generationcited by 99
  5. 2018Towards an Intelligent Edge: Wireless Communication Meets Machine Learningcited by 95
  6. 2020Federated Unsupervised Representation Learningcited by 93
  7. 2019Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attackscited by 81
  8. 2021A survey of deep neural network watermarking techniquescited by 73
  9. 2019Astraea: Self-balancing Federated Learning for Improving Classification Accuracy of Mobile Deep Learning Applicationscited by 64
  10. 2020Cost-Effective Federated Learning Designcited by 62
  11. 2020Ternary Compression for Communication-Efficient Federated Learningcited by 57
  12. 2017SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloudcited by 50
  13. 2017Model Extraction Warning in MLaaS Paradigmcited by 40
  14. 2018Digital Watermarking for Deep Neural Networkscited by 39
  15. 2018MLCapsule: Guarded Offline Deployment of Machine Learning as a Servicecited by 31
  16. 2021Auto-Split: A General Framework of Collaborative Edge-Cloud AIcited by 30
  17. 2020Towards Utilizing Unlabeled Data in Federated Learning: A Survey and Prospectivecited by 27
  18. 2020ES Attack: Model Stealing against Deep Neural Networks without Data Hurdlescited by 25
  19. 2019Bit Efficient Quantization for Deep Neural Networkscited by 14
  20. 2018IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classificationcited by 12
  21. 2019Federated Learning with Additional Mechanisms on Clients to Reduce Communication Costscited by 12
  22. 2016Accelerating Deep Convolutional Networks using low-precision and sparsitycited by 8
  23. 2021Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Datacited by 8
  24. 2020Exploiting Unlabeled Data in Smart Cities using Federated Learningcited by 6
  25. 2021Using AntiPatterns to avoid MLOps Mistakescited by 5
  26. 2019Personalized Query Auto-Completion Through a Lightweight Representation of the User Contextcited by 4
  27. 2020Towards a Two-Tier Hierarchical Infrastructure: An Offline Payment System for Central Bank Digital Currenciescited by 2
  28. 2021A Personalized Federated Learning Algorithm: an Application in Anomaly Detectioncited by 1
  29. 2022A VM/Containerized Approach for Scaling TinyML Applicationscited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2.

3 papers.

  1. 2022Edge Impulse: An MLOps Platform for Tiny Machine Learningcited by 24
  2. 2023MLOps: A Reviewcited by 16
  3. 2023Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Reviewcited by 9