Pedro Porto
Buarque de Gusmão
Lecturer in Computer Science, University of Surrey
About
I am a Lecturer in Computer Science at the University of Surrey, where I am part of the Nature Inspired Computing and Engineering (NICE) group. My research is on federated learning, machine unlearning, and privacy-preserving machine learning more broadly.
Before joining Surrey, I was a Senior Research Associate at the University of Cambridge, where I was one of the core developers of Flower, the open-source federated learning framework. Before that, I was a postdoctoral researcher at the University of Oxford, working on localisation and navigation for emergency responders. I hold a PhD from Politecnico di Torino and a BSc in Electrical Engineering from the University of São Paulo.
News
- PhD Scholarship opportunity soon
Selected publications
-
JMLR
A First Look into the Carbon Footprint of Federated Learning
Journal of Machine Learning Research, 24, 2023
-
USENIX Sec.
FedVal: Different Good or Different Bad in Federated Learning
32nd USENIX Security Symposium, 2023
-
ICCV
IEEE/CVF International Conference on Computer Vision, 2023
-
ICLR
ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity
International Conference on Learning Representations, 2022
-
ECCV
Federated Self-supervised Learning for Video Understanding
European Conference on Computer Vision, 2022
-
arXiv
Flower: A Friendly Federated Learning Research Framework
arXiv preprint arXiv:2007.14390, 2020