mlsanityData to 7 Oct 2026

EdgeOL: Efficient in-situ Online Learning on Edge Devices

arXiv 2401.16694 ↗First posted 30 Jan 2024cs.LG cs.CV cs.DCcited by 1

Not on the map. Why?

Abstract (arXiv)

Emerging applications, such as robot-assisted eldercare and object recognition, generally employ deep learning neural networks (DNNs) and naturally require: i) handling streaming-in inference requests and ii) adapting to possible deployment scenario changes. Online model fine-tuning is widely adopted to satisfy these needs. However, an inappropriate fine-tuning scheme could involve significant energy consumption, making it challenging to deploy on edge devices. In this paper, we propose EdgeOL, an edge online learning framework that optimizes inference accuracy, fine-tuning execution time, and energy efficiency through both inter-tuning and intra-tuning optimizations. Experimental results show that, on average, EdgeOL reduces overall fine-tuning execution time by 64%, energy consumption by 52%, and improves average inference accuracy by 1.75% over the immediate online learning strategy

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 61 of its 105 references that are in the map. First posted on arXiv 30 Jan 2024.

Builds on

61 of 105 references.

References · 61

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  6. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  7. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  8. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  9. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  10. 2019Similarity of Neural Network Representations Revisitedcited by 1,695
  11. 2020Knowledge Distillation: A Surveycited by 1,578
  12. 2020Energy-based Out-of-distribution Detectioncited by 1,296
38 more
  1. 2018Neural Network Acceptability Judgmentscited by 952
  2. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  3. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 895
  4. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  5. 2019Rigging the Lottery: Making All Tickets Winnerscited by 491
  6. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  7. 2019On the Efficacy of Knowledge Distillationcited by 377
  8. 2015Deep Learning with Limited Numerical Precisioncited by 368
  9. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  10. 2019Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgettingcited by 302
  11. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 287
  12. 2017Incremental Learning of Object Detectors without Catastrophic Forgettingcited by 208
  13. 2018Training Deep Neural Networks with 8-bit Floating Point Numberscited by 163
  14. 2019Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networkscited by 160
  15. 2019LAMOL: LAnguage MOdeling for Lifelong Language Learningcited by 156
  16. 2020Training with Quantization Noise for Extreme Model Compressioncited by 145
  17. 2016Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruningcited by 133
  18. 2020ATOM: Robustifying Out-of-distribution Detection Using Outlier Miningcited by 116
  19. 2019Latent Replay for Real-Time Continual Learningcited by 97
  20. 2019Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysiscited by 91
  21. 2021Achieving Forgetting Prevention and Knowledge Transfer in Continual Learningcited by 91
  22. 2020Multimodal Pretraining for Dense Video Captioningcited by 79
  23. 2019Towards Unified INT8 Training for Convolutional Neural Networkcited by 77
  24. 2015Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognitioncited by 67
  25. 2023Energy-based Out-of-Distribution Detection for Graph Neural Networkscited by 67
  26. 2018Online Model Distillation for Efficient Video Inferencecited by 60
  27. 2020Ekya: Continuous Learning of Video Analytics Models on Edge Compute Serverscited by 58
  28. 2022SparCL: Sparse Continual Learning on the Edgecited by 55
  29. 2020Continual Learning for Anomaly Detection in Surveillance Videoscited by 49
  30. 2021AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuningcited by 48
  31. 2019Rehearsal-Free Continual Learning over Small Non-I.I.D. Batchescited by 46
  32. 2021Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Taskscited by 46
  33. 2019Themis: Fair and Efficient GPU Cluster Schedulingcited by 43
  34. 2016The Curious Robot: Learning Visual Representations via Physical Interactionscited by 37
  35. 2019E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savingscited by 36
  36. 2020Real-Time Video Inference on Edge Devices via Adaptive Model Streamingcited by 29
  37. 2019OpenLORIS-Object: A Robotic Vision Dataset and Benchmark for Lifelong Deep Learningcited by 28
  38. 2021Distribution Adaptive INT8 Quantization for Training CNNscited by 27

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026DART-FL: Burst-Aware Multitask Federated Learning under Dynamic Inference Demand at the Edgecited by 0