Fetching the paper…

Reading the bibliography…

2021

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

Pellegrini, Lorenzo, Lomonaco, Vincenzo, Graffieti, Gabriele et al.

Original
PDF
Post on X

Understand

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.

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

Built on

Catastrophic interference in connectionist networks: The sequential learning problem
M. McCloskey and N. J. Cohen · 1989
Earlier work this paper cites.
CORe50: A New Dataset and Benchmark for Continuous Object Recognition
V. Lomonaco and D. Maltoni · 2017
Earlier work this paper cites.
Mobilenets: Efficient convolutional neural networks for mobile vision applications
Original
A. G. Howard, M. Zhu, B. Chen, et al · 2017
Earlier work this paper cites.

Similar

Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches
V. Lomonaco, D. Maltoni, and L. Pellegrini · 2020
Cited alongside, same era.
Latent replay for real-time continual learning
L. Pellegrini, G. Graffieti, V. Lomonaco, and D. Maltoni · 2020
Cited alongside, same era.
Avalanche: An End-to-End Library for Continual Learning
V. Lomonaco, L. Pellegrini, A. Cossu, et al · 2021
Cited alongside, same era.

Then

Replay in deep learning: Current approaches and missing biological elements
Original
T. L. Hayes, G. P. Krishnan, M. Bazhenov, et al · 2021
Closest in time.
Continual learning on the edge with tensorflow lite
Original
G. Demosthenous and V. Vassiliades · 2021
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…