Re-thinking Efficiency in Deep Learning under Accelerators and commodity and processors

Project Information

REDIAL

Grant agreement ID: 805194

DOI 10.3030/805194

EC signature date 10 October 2019

Start date 1 September 2020

End date 31 August 2025

Funded under

• EXCELLENT SCIENCE - European Research Council (ERC)

Total cost € 1 495 036,00

EU contribution € 1 495 036,00

Coordinated by

THE CHANCELLOR MASTERS AND SCHOLARS OF THE UNIVERSITY OF CAMBRIDGE
United Kingdom

Publications

Conference proceedings (15)

Secure aggregation for federated learning in flower

Author(s): Kwing Hei Li; Pedro Porto Buarque de Gusmão; Daniel J. Beutel; Nicholas D. Lane
Published in: Proceedings of the 2nd ACM International Workshop on Distributed Machine Learning, Issue 1, 2021, Page(s) 8-14
Publisher: ACM
DOI: 10.48550/arxiv.2205.06117

PROSPECT PRUNING: FINDING TRAINABLE WEIGHTSAT INITIALIZATION USING META-GRADIENTS

Author(s): Milad Alizadeh, Shyam A. Tailor, Luisa Zintgraf 3 Joost van Amersfoort 1 Sebastian Farquhar 1 Nicholas Donald Lane 2,4 Yarin Gal 1
Published in: International Conference on Learning Representations, Issue 1, 2022
Publisher: ICLR

Differentiable Neural Network Pruning to Enable Smart Applications on Microcontrollers

Author(s): Edgar Liberis, Nicholas D Lane
Published in: 2023, ISSN 2474-9567
Publisher: ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies IMWUT
DOI: 10.48550/arxiv.2110.08350

Federated Self-supervised Speech Representations: Are We There Yet?

Author(s): Yan Gao, Javier Fernandez-Marques, Titouan Parcollet, Abhinav Mehrotra, Nicholas D. Lane
Published in: 2022
Publisher: Interspeech 2022

Di!erentiable Neural Network Pruning to Enable Smart Applicationson Microcontrollers

Author(s): EDGAR LIBERIS, NICHOLAS D. LANE
Published in: ACM IMWUT Journal, Issue 1, 2022
Publisher: ACM

Deep learning on microcontrollers

Author(s): Svoboda, Filip; Fernandez-Marques, Javier; Liberis, Edgar; Lane, Nicholas D.
Published in: isbn: 9781450392549, Issue 1, 2022
Publisher: 2nd Workshop on Machine Learning and Systems, EuroMLSys

Gradient-less Federated Gradient Boosting Tree with Learnable Learning Rates

Author(s): Chenyang Ma, Xinchi Qiu, Daniel Beutel, Nicholas Lane
Published in: 2023
Publisher: 3rd Workshop on Machine Learning and Systems

Federated Self-supervised Learning for Video Understanding

Author(s): Yasar Abbas Ur Rehman, Yan Gao, Jiajun Shen, Pedro Porto Buarque de Gusmão, Nicholas Lane
Published in: 2022
Publisher: 17th European Conference on Computer Vision

ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity

Author(s): Qiu, Xinchi; Fernandez-Marques, Javier; Gusmao, Pedro PB; Gao, Yan; Parcollet, Titouan; Lane, Nicholas Donald
Published in: 2022
Publisher: International Conference on Learning Representations
DOI: 10.48550/arxiv.2208.02507

End-to-End Speech Recognition from Federated Acoustic Models

Author(s): Yan Gao, Titouan Parcollet, Salah Zaiem, Javier Fernandez-Marques, Pedro P. B. de Gusmao, Daniel J. Beutel, Nicholas Lane
Published in: 2022
Publisher: IEEE International Conference on Acoustics, Speech and Signal Processing

μNAS: Constrained Neural Architecture Search for Microcontrollers

Author(s): Edgar Liberis, Łukasz Dudziak, Nicholas D. Lane
Published in: Proceedings of the 1st Workshop on Machine Learning and Systems (EuroMLSys), 2021
Publisher: ACM

Can Fair Federated Learning reduce the need for Personalisation?

Author(s): Alex Iacob, Pedro Porto Buarque Gusmão, Nicholas Lane
Published in: 2023
Publisher: 3rd Workshop on Machine Learning and Systems

Protea: Client profiling within federated systems using flower

Author(s): Wanru Zhao, Xinchi Qiu, Javier Fernandez-Marques, Pedro PB de Gusmão, Nicholas D Lane
Published in: 2022
Publisher: 1st ACM Workshop on Data Privacy and Federated Learning Technologies for Mobile Edge Network

Deep Learning on Microcontrollers: A Studyon Deployment Costs and Challenges

Author(s): Filip Svoboda Javier Fernandez-Marques Edgar Liberis Nicholas D. Lane
Published in: Proceedings of EuroMLSys, 2022
Publisher: ACM
DOI: 10.1145/3517207.3526978

FedVal: Different good or different bad in federated learning

Author(s): Viktor Valadi, Xinchi Qiu, Pedro Porto Buarque de Gusmão, Nicholas D. Lane, Mina Alibeigi
Published in: 2023
Publisher: 32nd USENIX Security Symposium

Peer reviewed articles (2)

MobiVQA: Efficient On-Device Visual Question Answering

Author(s): Qingqing Cao, Prerna Khanna, Nicholas D. Lane, Aruna Balasubramanian
Published in: ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, Issue 1, 2022, Page(s) Volume 6 Issue 2. July 2022, ISSN 2474-9567
Publisher: ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies IMWUT

A first look into the carbon footprint of federated learning

Author(s): Xinchi Qiu, Titouan Parcollet, Javier Fernandez-Marques, Pedro PB de Gusmao, Yan Gao, Daniel J Beutel, Taner Topal, Akhil Mathur, Nicholas D Lane
Published in: Journal of Machine Learning Research, 2023, Page(s) Volume 24 Issue 1. January 2023, ISSN 1533-7928
Publisher: Journal of Machine Learning Research

Other (1)

Pex: Memory-efficient Microcontroller Deep Learning through Partial Execution

Author(s): Edgar Liberis, Nicholas D. Lane
Published in: 2022
Publisher: ArXiv pre-print