Research Seminar - Federated Learning: A New Era Learning Architecture for Multi-Discipline Applications and Its Challenges

Federated Learning (FL) is a distributed machine learning technique where multiple devices (such as smartphones or IoT devices) train a shared global model by using their local data. FL claims that the data privacy of local participants is preserved well because local data will not be shared with either the server-side or other training participants. Therefore, it could be applied in multi-discipline application for solving the problem of data limitation and computation power limitation, as well as the private data will be well preserved by the training process. However, FL is not that perfect, challenges still exist. In this presentation, Dr. Di Wu will discuss the FL applications and challenges in his research and introduce his recent research on addressing the challenges.

Dr. Di Wu is a Lecturer at the School of Mathematics, Physics, and Computing, the University of Southern Queensland. Prior to that, he was a Researcher at the Australian Institute for Machine Learning (AIML) & School of Computer Science, University of Adelaide, Adelaide, Australia. Previous to this, he was an Associate Research Fellow, Artificial Intelligence at Deakin Blockchain Innovation Lab, School of Information Technology, Deakin University, Melbourne, Australia, and worked as a Postdoc Fellow at the School of Computer Science, University of Technology Sydney (UTS), Sydney, Australia. He has more than 10 years of experience in research & development and academia. He has substantial industry experience in large project management, software development, and large system maintenance experience while working on various projects at China Telecom (Global 500), Shanghai. His research area focuses on applying AI on edge devices and AI applications. The project SharkSpotter and Codebots he worked as Chief Investigator awarded multiple awards including The Australian Information Industry Association (AIIA) NSW iAwards 2018 in Research and Development Project of the Year, Artificial Intelligence or Machine Learning Innovation of the Year, and Community Service Markets. Additionally, the SharkSpotter Project is also a winner of National iAwards 2018 in the Artificial Intelligence or Machine Learning Innovation of the Year, Merit Award at Asia Pacific ICT Alliance Awards (APICTA) 2018, and Australian Association for Unmanned Systems (AAUS) industry awards 2020. The Codebots projects received the Start-up of The year Queensland State iAward in 2020. He has published over 20 papers in refereed books, conferences, and journals and a reviewer for multi-discipline conferences and journals to serve the research community. He has served as a special session chair for IJCNN. He also serves as a reviewer for many top-tier academic conferences and journals, such as CoRL, PR, TETCI, and so on.

For more information, please contact Di Wu.