Coming up: The IEEE Communication Theory Technical Committee (CTTC) invites you to the “2+1” online event
Title: Federated Learning and Analytics
Date/Time: October 23, 2023 9.00am – 10:30am PT / 4.00pm – 5:30pm UTC / 6.00pm – 7:30pm CEST
Recording of the event: LINK
To attend the event, register by filling out the following form (registration deadline October 21, 11:59pm PT): LINK
Detailed Agenda (time in PT)
|Welcome Speech, by Ayfer Ozgur
|Invited Talk I by Peter Kairouz
|Invited Talk II by Deniz Gündüz
|Panel Discussions and Questions (Including the ones collected already). Moderator: Ayfer Ozgur
Moderator: Ayfer Özgür (Stanford University, USA). Ayfer Özgür is an Associate Professor with the Department of Electrical Engineering, Stanford University, where she is the Chambers Faculty Scholar with the School of Engineering. Her research interests include information theory, wireless communication, statistics, and machine learning. She received the EPFL Best Ph.D. Thesis Award in 2010, the NSF CAREER Award in 2013, the Okawa Foundation Research Grant, the Faculty Research Awards from Google and Facebook, and the IEEE Communication Theory Technical Committee (CTTC) Early Achievement Award in 2018. She was selected as the Inaugural Goldsmith Lecturer of the IEEE ITSoc in 2020. In 2023, she also received the Stanford University Electrical Engineering Chair’s award for Outstanding Contributions to Undergraduate Education.
Invited Talk I: Federated Learning in Practice: Reflections and Projections, by Peter Kairouz (Google, USA)
Introduced in 2016 as a privacy-enhancing technique, federated learning has made significant strides in recent years. This presentation offers a retrospective view, delving into the foundational principles of federated learning, encompassing the diverse variants and definitions presented in the ‘Advances and Open Problems in Federated Learning’ manuscript. We highlight key milestones, spotlighting the major implementations within the Google ecosystem and explaining the meticulous efforts dedicated to the fusion of federated learning with secure aggregation and formal differential privacy guarantees. We also touch on the nascent trends on the horizon and provide insights into the evolving landscape of federated learning and its definitions. These evolutionary steps are essential to perpetuate its practical impact.
Peter Kairouz is a Staff Research Scientist at Google, where he focuses on researching and building private, secure, and trustworthy AI technologies. Before joining Google, he was a Postdoctoral Research Fellow at Stanford University. He received his Ph.D. in electrical and computer engineering from the University of Illinois at Urbana-Champaign (UIUC). He is the recipient of the 2012 Roberto Padovani Scholarship from Qualcomm’s Research Center, the 2015 ACM SIGMETRICS Best Paper Award, the 2015 Qualcomm Innovation Fellowship Finalist Award, the 2016 Harold L. Olesen Award for Excellence in Undergraduate Teaching from UIUC, and the 2021 ACM Conference on Computer and Communications Security (CCS) Best Paper Award.
Invited Talk II: Federated Learning over Wireless Networks, by Deniz Gündüz (Imperial College London, UK)
Mobile devices collect massive amounts of data, opening up new potentials for machine learning applications. Federated edge learning (FEEL) can benefit from both the data and processing power distributed across wireless devices, but this brings about many challenges. In this talk, I will focus on the communication aspects of FEEL, particularly focusing on the interference and resource management issues of federated learning among devices sharing the same wireless medium. I will show that FEEL requires a completely fresh look at wireless access and interference management, and highlight novel approaches such as over-the-air computing, update-aware scheduling, and hierarchical FEEL.
Deniz Gündüz is a Professor of Information Processing in the Electrical and Electronic Engineering Department at Imperial College London, UK, where he leads the Information Processing and Communications Lab (IPC-Lab). His research interests lie in the areas of communications and information theory, machine learning, and privacy. Dr. Gündüz is a Fellow of the IEEE, and an elected member of the IEEE Signal Processing Society Signal Processing for Communications and Networking (SPCOM), and Machine Learning for Signal Processing (MLSP) Technical Committees. He serves in editorial roles for the IEEE Transactions on Information Theory (area editor), IEEE Transactions on Communications (area editor), IEEE Transactions on Wireless Communications (editor), IEEE Journal on Selected Areas in Information Theory (guest editor). He is the recipient of the IEEE Communications Society – Communication Theory Technical Committee (CTTC) Early Achievement Award in 2017, Starting (2016), Consolidator (2022) and Proof-of-Concept (2023) Grants of the European Research Council (ERC), and has co-authored several award-winning papers, including the IEEE Communications Society – Young Author Best Paper Award (2022), and IEEE International Conference on Communications Best Paper Award (2023). In 2023, he also received the Imperial College London – President’s Award for Excellence in Research Supervision.