About
I'm a Senior Research Scientist at Nokia Bell Labs in Cambridge, where I invent and build efficient solutions for machine learning.
My area of expertise? It's all about federated learning, making ML work harder with less, and tackling the tricky stuff like uncertainty estimation.
Essentially, I'm working on the algorithms and systems that are going to make machine learning models faster, better, and more reliable for everyone.
I completed my Ph.D. in Computer Science at the University of Cambridge, under the supervision of Prof. Cecilia Mascolo.
My research focused on developing techniques to provide efficient, accurate and uncertainty-aware mobile sensing and health applications.
The goal was to enhance these applications with the robustness needed to withstand real-world challenges, such as distributional shifts and adversarial attacks.
Starting my journey at the University of Bologna, where I earned my BEng and MEng in Computer Engineering, I've since gathered diverse experience across the tech industry.
My roles have ranged from research in ML-based user behavior analysis at T-Labs, efficient ML at Nokia Bell Labs,
and adversarial mitigation at Arm, to software engineering in high-performance computing at Ellexus (now Altair),
open-source data analytics at Connected Places Catapult, and spatial analytics at GeoSpock.
By the way, check out my publications.
Publications
UR2M: Uncertainty and Resource-Aware Event Detection on Microcontrollers.
Hong Jia, Young D Kwon, Dong Ma, Nhat Pham, Lorena Qendro, Tam Vu, Cecilia Mascolo
IEEE International Conference on Pervasive Computing and Communications, PerCom'24, Biarritz, France, March 2024
Uncertainty-aware Health Diagnostics via Class-balanced Evidential Deep Learning.
Tong Xia, Ting Dang, Jing Han, Lorena Qendro, Cecilia Mascolo
IEEE Journal of Biomedical and Health Informatics, February 2024
Balancing Continual Learning and Fine-tuning for Human Activity Recognition.
Chi Ian Tang, Lorena Qendro, Dimitris Spathis, Fahim Kawsar, Akhil Mathur, Cecilia Mascolo
Human-Centric Representation Learning Workshop, AAAI'24, Vancouver, Canada, February 2024
Kaizen: Practical Self-Supervised Continual Learning With Continual Fine-Tuning.
Chi Ian Tang, Lorena Qendro, Dimitris Spathis, Fahim Kawsar, Cecilia Mascolo, Akhil Mathur
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, WACV'24, Hawaii, USA, January 2024
Uncertainty-Informed On-Device Personalisation Using Early Exit Networks on Sensor Signals.
Sotirios Vavaroutas, Lorena Qendro, Cecilia Mascolo
Proceedings of the 31st European Signal Processing Conference, EUSIPCO'23, Helsinki, Finland, September 2023
Uncertainty Estimation with Data Augmentation for Active Learning Tasks on Health Data.
Sotirios Vavaroutas, Lorena Qendro, Cecilia Mascolo
Proceedings of the 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society, EMBC'23, Sydney, Australia, July 2023
Hybrid-EDL: Improving Evidential Deep Learning for Uncertainty Quantification on Imbalanced Data.
Tong Xia, Jing Han, Lorena Qendro, Ting Dang, Cecilia Mascolo
Trustworthy and Socially Responsible Machine Learning Workshop, NeurIPS 2022, New Orleans, Louisiana, USA, December 2022
Efficient, robust and uncertainty aware mobile health.
Lorena Qendro
PhD Thesis, University of Cambridge, September 2022
Mobile health with head-worn devices: Challenges and opportunities.
Andrea Ferlini*, Dong Ma*, Lorena Qendro*, Cecilia Mascolo
IEEE Pervasive Computing, Volume: 21, Issue: 3, 01 July-Sept. 2022
Towards Adversarial Mitigation with Early Exit Ensembles.
Lorena Qendro, Cecilia Mascolo
Proceedings of the 44th IEEE International Engineering in Medicine and Biology Conference, EMBC'22, Glasgow, UK, July 2022
Robust and Efficient Uncertainty Aware Biosignal Classification via Early Exit Ensembles.
Alexander Campbell*, Lorena Qendro*, Pietro Liò, Cecilia Mascolo
IEEE International Conference on Acoustics, Speech, & Signal Processing, ICASSP'22, Singapore, May 2022
Enhancing the Security & Privacy of Wearable Brain-Computer Interfaces.
Zahra Tarkhani*, Lorena Qendro*, Malachy O'Connor Brown, Oscar Hill, Cecilia Mascolo, Anil Madhavapeddy
Preprint, March 2022
Early Exit Ensembles for Uncertainty Quantification.
[Best Thematic Paper Award]
Lorena Qendro*, Alexander Campbell*, Pietro Liò, Cecilia Mascolo
Proceedings of Machine Learning for Health, ML4H '21, December 2021
Uncertainty-Aware COVID-19 Detection from Imbalanced Sound Data.
Tong Xia, Jing Han, Lorena Qendro, Ting Dang, Cecilia Mascolo
Proceedings of the Annual Conference of the International Speech Communication Association, Interspeech '21, Brno, Czechia, September 2021
High Frequency EEG Artifact Detection with Uncertainty via Early Exit Paradigm.
Lorena Qendro*, Alexander Campbell*, Pietro Liò, Cecilia Mascolo
The Thirty-eighth International Conference on Machine Learning, Workshop on Human In the Loop Learning, ICML '21, July 2021
Stochastic-Shield: A Probabilistic Approach Towards Training-Free Adversarial Defense in Quantized CNNs.
Lorena Qendro, Sangwon Ha, René de Jong, Partha Maji
Proceedings of the 1st Workshop on Security and Privacy for Mobile AI (MAISP), MobiSys '21, Mars, Solar System, June 2021
The Benefit of the Doubt: Uncertainty Aware Sensing for Edge Computing Platforms.
Lorena Qendro, Jagmohan Chauhan, Alberto Gil CP Ramos, Cecilia Mascolo
The Sixth ACM/IEEE Symposium on Edge Computing, SEC '21, San Jose, California, USA, December 2021
ePerceptive: energy reactive embedded intelligence for batteryless sensors.
Alessandro Montanari, Manuja Sharma, Dainius Jenkus, Mohammed Alloulah, Lorena Qendro, Fahim Kawsar
Proceedings of the 18th Conference on Embedded Networked Sensor Systems, Sensys '20, November 2020
Uncertianty Aware Mobile Sensing.
Lorena Qendro, Jagmohan Chauhan, Cecilia Mascolo
Second UK Mobile, Wearable and Ubiquitous Systems Research Symposium, Oxford, UK, July 2019
DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices.
Nicholas D. Lane, Sourav Bhattacharya, Petko Georgiev, Claudio Forlivesi, Lei Jiao, Lorena Qendro, Fahim Kawsar
15th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN '16, Vienna, Austria, April 2016
DeepEar: robust smartphone audio sensing in unconstrained acoustic environments using deep learning.
[Best Paper Award]
Nicholas D. Lane, Petko Georgiev, Lorena Qendro
Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing,
UbiComp '15, Osaka, Japan, September 2015