Thu, February 29, 8:30 PM
90 MINUTES
Multi-Device Intelligence with a Data-Centric Approach to Federated Learning

To improve human experience within a multi-device environment, it is important to learn from various modalities and in diverse circumstances. Two significant challenges are, first, the limited availability of data for multimodal learning, and second, the constrained computational capabilities of edge devices when it comes to training deep neural networks. Join our discussion on the efficient and effective training of neural networks using data captured by edge devices, covering topics such as data selection, model partitioning, missing modalities, label efficiency, and more.

Mohammad Malekzadeh

Senior Research Scientist @ Nokia Bell Labs

Mohammad Malekzadeh is a Senior Research Scientist in the Device Research department at Nokia Bell Labs in Cambridge, UK. He leads the Device Intelligence team, focusing on Machine Learning solutions for personal devices, with an emphasis on efficiency, collaboration, adaptability, and privacy. Before joining Bell Labs, He worked as a Postdoctoral Research Associate at Imperial College London's Information Processing and Communications Lab, closely collaborating with Prof. Deniz Gunduz on Privacy-Preserving and Trustworthy Machine Learning. He pursued his PhD in Computer Science at Queen Mary University of London as a member of the Centre for Intelligent Sensing, concurrently holding a Research Assistant position at Imperial College London contributing to the Databox Project in the Systems and Algorithms Laboratory. In his PhD, he had the chance to work with great advisors, Prof. Hamed Haddadi, Dr. Richard G. Clegg, and Prof. Andrea Cavallaro, on developing Machine Learning Algorithms for Privacy-Preserving Personal Data Analytics, particularly for data captured by mobile and wearable devices. During his PhD journey, he interned at Brave Software Research, where he explored privacy-preserving techniques to improve content personalization in web browsers. Prior to PhD, he earned an MSc degree in Computer Engineering from Sharif University of Technology in Iran.