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

Información del proyecto

REDIAL

Identificador del acuerdo de subvención: 805194

DOI

10.3030/805194

Proyecto cerrado

Fecha de la firma de la CE 10 Octubre 2019

Fecha de inicio 1 Septiembre 2020

Fecha de finalización 31 Agosto 2025

Financiado con arreglo a

• EXCELLENT SCIENCE - European Research Council (ERC)

Coste total

€ 1 495 036,00

Aportación de la UE

€ 1 495 036,00

Coordinado por

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

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Publicaciones

Conference proceedings (15)

Secure aggregation for federated learning in flower

Autores: Kwing Hei Li; Pedro Porto Buarque de Gusmão; Daniel J. Beutel; Nicholas D. Lane
Publicado en: Proceedings of the 2nd ACM International Workshop on Distributed Machine Learning, Edición 1, 2021, Página(s) 8-14
Editor: ACM
DOI: 10.48550/arxiv.2205.06117

PROSPECT PRUNING: FINDING TRAINABLE WEIGHTSAT INITIALIZATION USING META-GRADIENTS

Autores: Milad Alizadeh, Shyam A. Tailor, Luisa Zintgraf 3 Joost van Amersfoort 1 Sebastian Farquhar 1 Nicholas Donald Lane 2,4 Yarin Gal 1
Publicado en: International Conference on Learning Representations, Edición 1, 2022
Editor: ICLR

Differentiable Neural Network Pruning to Enable Smart Applications on Microcontrollers

Autores: Edgar Liberis, Nicholas D Lane
Publicado en: 2023, ISSN 2474-9567
Editor: ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies IMWUT
DOI: 10.48550/arxiv.2110.08350

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

Autores: Yan Gao, Javier Fernandez-Marques, Titouan Parcollet, Abhinav Mehrotra, Nicholas D. Lane
Publicado en: 2022
Editor: Interspeech 2022

Di!erentiable Neural Network Pruning to Enable Smart Applicationson Microcontrollers

Autores: EDGAR LIBERIS, NICHOLAS D. LANE
Publicado en: ACM IMWUT Journal, Edición 1, 2022
Editor: ACM

Deep learning on microcontrollers

Autores: Svoboda, Filip; Fernandez-Marques, Javier; Liberis, Edgar; Lane, Nicholas D.
Publicado en: isbn: 9781450392549, Edición 1, 2022
Editor: 2nd Workshop on Machine Learning and Systems, EuroMLSys

Gradient-less Federated Gradient Boosting Tree with Learnable Learning Rates

Autores: Chenyang Ma, Xinchi Qiu, Daniel Beutel, Nicholas Lane
Publicado en: 2023
Editor: 3rd Workshop on Machine Learning and Systems

Federated Self-supervised Learning for Video Understanding

Autores: Yasar Abbas Ur Rehman, Yan Gao, Jiajun Shen, Pedro Porto Buarque de Gusmão, Nicholas Lane
Publicado en: 2022
Editor: 17th European Conference on Computer Vision

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

Autores: Qiu, Xinchi; Fernandez-Marques, Javier; Gusmao, Pedro PB; Gao, Yan; Parcollet, Titouan; Lane, Nicholas Donald
Publicado en: 2022
Editor: International Conference on Learning Representations
DOI: 10.48550/arxiv.2208.02507

End-to-End Speech Recognition from Federated Acoustic Models

Autores: Yan Gao, Titouan Parcollet, Salah Zaiem, Javier Fernandez-Marques, Pedro P. B. de Gusmao, Daniel J. Beutel, Nicholas Lane
Publicado en: 2022
Editor: IEEE International Conference on Acoustics, Speech and Signal Processing

μNAS: Constrained Neural Architecture Search for Microcontrollers

Autores: Edgar Liberis, Łukasz Dudziak, Nicholas D. Lane
Publicado en: Proceedings of the 1st Workshop on Machine Learning and Systems (EuroMLSys), 2021
Editor: ACM

Can Fair Federated Learning reduce the need for Personalisation?

Autores: Alex Iacob, Pedro Porto Buarque Gusmão, Nicholas Lane
Publicado en: 2023
Editor: 3rd Workshop on Machine Learning and Systems

Protea: Client profiling within federated systems using flower

Autores: Wanru Zhao, Xinchi Qiu, Javier Fernandez-Marques, Pedro PB de Gusmão, Nicholas D Lane
Publicado en: 2022
Editor: 1st ACM Workshop on Data Privacy and Federated Learning Technologies for Mobile Edge Network

Deep Learning on Microcontrollers: A Studyon Deployment Costs and Challenges

Autores: Filip Svoboda Javier Fernandez-Marques Edgar Liberis Nicholas D. Lane
Publicado en: Proceedings of EuroMLSys, 2022
Editor: ACM
DOI: 10.1145/3517207.3526978

FedVal: Different good or different bad in federated learning

Autores: Viktor Valadi, Xinchi Qiu, Pedro Porto Buarque de Gusmão, Nicholas D. Lane, Mina Alibeigi
Publicado en: 2023
Editor: 32nd USENIX Security Symposium

Peer reviewed articles (2)

MobiVQA: Efficient On-Device Visual Question Answering

Autores: Qingqing Cao, Prerna Khanna, Nicholas D. Lane, Aruna Balasubramanian
Publicado en: ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, Edición 1, 2022, Página(s) Volume 6 Edición 2. July 2022, ISSN 2474-9567
Editor: ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies IMWUT

A first look into the carbon footprint of federated learning

Autores: Xinchi Qiu, Titouan Parcollet, Javier Fernandez-Marques, Pedro PB de Gusmao, Yan Gao, Daniel J Beutel, Taner Topal, Akhil Mathur, Nicholas D Lane
Publicado en: Journal of Machine Learning Research, 2023, Página(s) Volume 24 Edición 1. January 2023, ISSN 1533-7928
Editor: Journal of Machine Learning Research

Other (1)

Pex: Memory-efficient Microcontroller Deep Learning through Partial Execution

Autores: Edgar Liberis, Nicholas D. Lane
Publicado en: 2022
Editor: ArXiv pre-print