mlsanityData to 13 Oct 2026

Continual Learning at the Edge: Real-Time Training on Smartphone Devices

arXiv 2105.13127 ↗First posted 24 May 2021cs.LG cs.AI cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

On-device training for personalized learning is a challenging research problem. Being able to quickly adapt deep prediction models at the edge is necessary to better suit personal user needs. However, adaptation on the edge poses some questions on both the efficiency and sustainability of the learning process and on the ability to work under shifting data distributions. Indeed, naively fine-tuning a prediction model only on the newly available data results in catastrophic forgetting, a sudden erasure of previously acquired knowledge. In this paper, we detail the implementation and deployment of a hybrid continual learning strategy (AR1*) on a native Android application for real-time on-device personalization without forgetting. Our benchmark, based on an extension of the CORe50 dataset, shows the efficiency and effectiveness of our solution.

Key facts. Cited by 20 papers in the map (data through 13 Oct 2026). Builds on 7 of its 8 references that are in the map. First posted on arXiv 24 May 2021.

Builds on

7 of 8 references.

References · 7

  1. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,836
  2. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 287
  3. 2021Avalanche: an End-to-End Library for Continual Learningcited by 124
  4. 2019Latent Replay for Real-Time Continual Learningcited by 97
  5. 2021Replay in Deep Learning: Current Approaches and Missing Biological Elementscited by 71
  6. 2019Rehearsal-Free Continual Learning over Small Non-I.I.D. Batchescited by 46
  7. 2021Continual Learning on the Edge with TensorFlow Litecited by 9

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 5; 2023: 4; 2024: 6; 2025: 3; 2026: 2.

20 papers.

Sort:

By area:

  1. 2023When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directionscited by 84
  2. 2022SparCL: Sparse Continual Learning on the Edgecited by 55
  3. 2022Online Continual Learning for Embedded Devicescited by 49
  4. 2024One-stage Prompt-based Continual Learningcited by 14
  5. 2024Continual Learning in the Frequency Domaincited by 12
  6. 2023Cost-effective On-device Continual Learning over Memory Hierarchy with Mirocited by 10
  7. 2023Online Continual Learning for Robust Indoor Object Recognitioncited by 9
  8. 2023Online Continual Learning in Keyword Spotting for Low-Resource Devices via Pooling High-Order Temporal Statisticscited by 9
  9. 2025When Continue Learning Meets Multimodal Large Language Model: A Surveycited by 9
  10. 2022Generative Negative Replay for Continual Learningcited by 4
  11. 2024Exploring the Stability Gap in Continual Learning: The Role of the Classification Headcited by 4
  12. 202412 mJ per Class On-Device Online Few-Shot Class-Incremental Learningcited by 3
8 more
  1. 2022Increasing Depth of Neural Networks for Life-long Learningcited by 1
  2. 2024EdgeOL: Efficient in-situ Online Learning on Edge Devicescited by 1
  3. 2025Efficient Continual Learning through Frequency Decomposition and Integrationcited by 1
  4. 2022Federated Learning -- Methods, Applications and beyondcited by 0
  5. 2024Data-Free Generative Replay for Class-Incremental Learning on Imbalanced Datacited by 0
  6. 2025Online Continual Learning on Intel Loihi 2 via a Co-designed Spiking Neural Networkcited by 0
  7. 2026Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edgecited by 0
  8. 2026HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learningcited by 0