Publications

Royson Lee, Javier Fernandez-Marques, Shell Xu Hu, Da Li, Stefanos Laskaridis, Łukasz Dudziak, Timothy Hospedales, Ferenc Huszár, Nicholas D. Lane. “Recurrent Early Exits for Federated Learning with Heterogeneous Clients” International Conference on Machine Learning (ICML) [arXiv]

Javier Fernandez-Marques, Ahmed F. AbouElhamayed, Nicholas D. Lane and Mohamed S. Abdelfattah. “Are We There Yet? Product Quantization and its Hardware Acceleration” [arXiv]
Stylianos I. Venieris, Javier Fernandez-Marques, Nicholas D. Lane. “Mitigating Memory Wall Effects in CNN Engines with On-the-Fly Weights Generation” ACM TODAES [Link]

Lukasz Dudziak*, Stefanos Laskaridis*, Javier Fernandez-Marques*. “FedorAS: Federated Architecture Search under system heterogeneity” [arXiv]
Zicheng Liu, Da Li, Javier Fernandez-Marques, Stefanos Laskaridis, Yan Gao, Łukasz Dudziak, Stan Z Li, Shell Xu Hu, Timothy Hospedales “Federated Learning for Inference at Anytime and Anywhere” [arXiv]
Yan Gao, Javier Fernandez-Marques, Titouan Parcollet, Pedro Porto Buarque de Gusmao and Nicholas D. Lane. “Match to Win: Analysing Sequences Lengths for Efficient Self-supervised Learning in Speech and Audio” IEEE SLT 2022 [arXiv]
Yan Gao, Javier Fernandez-Marques, Titouan Parcollet, Abhinav Mehrotra and Nicholas D. Lane. “Federated Self-supervised Speech Representations: Are We There Yet?” INTERSPEECH 2022 [arXiv]
Xinchi Qiu*, Javier Fernandez-Marques*, Pedro Porto Buarque de Gusmao, Yan Gao, Titouan Parcollet, and Nicholas D. Lane. “ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity”. International Conference on Learning Representatioins (ICLR), 2022 [OpenReviw]

Akhil Mathur, Daniel J. Beutel, Pedro Porto Buarque de Gusmão, Javier Fernandez-Marques, Taner Topal, Xinchi Qiu, Titouan Parcollet, Yan Gao and Nicholas D. Lane. “On-device Federated Learning with Flower”. In 2nd On-device Intelligence Workshop (MLSys) 2021 [arXiv]
Yan Gao, Titouan Parcollet, Salah Zaiem, Javier Fernandez-Marques, Pedro P. B. de Gusmao, Daniel J. Beutel and Nicholas D. Lane. “End-to-End Speech Recognition from Federated Acoustic Models” [arXiv]
Xinchi Qiu, Titouan Parcollet, Javier Fernandez-Marques, Pedro Porto Buarque de Gusmao, Daniel J. Beutel, Taner Topal, Akhil Mathur and Nicholas D. Lane. “A First Look into the Carbon Footprint of Federated Learning” [arXiv]

Stylianos I. Venieris*, Javier Fernandez-Marques* and Nicholas D. Lane. “unzipFPGA: Enhancing FPGA-based CNN Engines with On-the-fly Weights Generation.” IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM), 2021 [arXiv]
Shyam A. Tailor*, Javier Fernandez-Marques* and Nicholas D. Lane. “Degree-Quant: Quantization-Aware Training for Graph Neural Networks.” International Conference on Learning Representations (ICLR), 2021 [arXiv]. Also in Graph Representation Learning and Beyond Workshop (ICMLw), 2020 [Link]

Javier Fernandez-Marques, Paul N. Whatmough, Andrew Mundy and Matthew Mattina. “Searching for Winograd-aware Quantized Networks.” Conference on Machine Learning and Systems (MLSys), 2020 [Link]
Milad Alizadeh, Javier Fernandez-Marques, Nicholas D. Lane and Yarin Gal. “A Systematic Study of Binary Neural Networks’ Optimisation.” International Conference on Learning Representations (ICLR), 2019 [Link]

Javier Fernandez-Marques, Vincent W.-S. Tseng, Sourav Bhattacharya and Nicholas D. Lane. “On-the-fly deterministic binary filters for memory efficient keyword spotting applications on embedded devices”. International Workshop on Embedded and Mobile Deep Learning (EMDL-MobiSys), 2018 [Link]
Javier Fernandez-Marques, Vincent W.-S. Tseng, Sourav Bhattacharya and Nicholas D. Lane. “BinaryCmd: Keyword Spotting with deterministic binary basis”. Conference on Systems and Machine Learning (SysML), 2018 [Link]
Vincent Tseng, S. Bhattacharya, Javier Fernandez-Marques, Milad Alizadeh, Catherine Tong and Nicholas D. Lane. “Deterministic Binary Filters for Convolutional Neural Networks.” International Joint Conference on Artificial Intelligence (IJCAI), 2018 [Link]

Marting Maška, Cristina Ederra, Javier Fernandez-Marques, Arrate Muñoz-Barrutia, Michal Kozubek and Carlos Ortiz-de-Solórzano. “Quantification of the 3D Collagen Network Geometry in Confocal Reflection Microscopy”. International Conference on Image Processing (ICIP), 2015 [Link]
Maria Anguiano, Carlos Castilla, Martin Maška, Cristina Ederra, Javier Fernandez-Marques, R.Peláez, Ana Rozaut, Arrate Muñoz-Barrutia, M. Kozubek and Carlos Ortiz-de-Solórzano. “Characterization of the Role of Collagen Network Structure and Composition in Cancer Cell Migration”. International conf. of the IEEE Engineering in Medicine and Biology Society (EMBC), 2015 [Link]