Workshop on Federated Learning in Australasia: When FL meets Foundation Models in Conjunction with AJCAI 2024 (FL@FM-AJCAI'24)


Workshop Date: 09:00-17:00, Monday, November 25, 2024
Venue: Room 03.05, Level 3, RMIT University Building 80, 445 Swanston Street, Melbourne, Australia

Workshop Program (Monday, November 25, 2024)

  
Time Activity
  
09:00 – 10:00 Tutorial - Part 1: Introduction of Federated Machine Learning Research, by Guodong Long
10:00 – 10:30 Coffee Break
10:30 – 11:30 Tutorial - Part 2: Introduction of Federated Machine Learning Research, by Guodong Long
11:30 – 12:30 Keynote: Federated Learning Research from Cybersecurity Perspective, by Xingliang Yuan
12:30 – 13:30 Lunch Break
13:30 – 14:30 Keynote: Challenges and Opportunities for Federated Learning in the Age of Foundation Models, by Han Yu
14:30 – 15:00 Invited Presentation: Federated Recommendation, by Zhiwei Li
15:00 – 15:30 Coffee Break
15:30 – 17:00 Invited Presentations (15 min per talk + 3 min Q&A)
  1. A Unified Solution to Diverse Heterogeneities in One-shot Federated Learning, by Jun Bai
  2. Personalized Adapter for Large Meteorology Model on Devices: Towards Weather Foundation Models, by Shengchao Chen
  3. Dual-Personalizing Adapter for Federated Foundation Models, by Yiyuan Yang
  4. Multi-Level Additive Modeling for Structured Non-IID FL, by Shutong Chen
  5. Personalized Interpretation on Federated Learning, by Peng Yan
   

Overview

The aim of this workshop is to bring together academic researchers and industry professionals within the Australasian region to discuss, explore, and address the potentials and challenges of incorporating federated learning (FL) techniques with foundation models. This workshop serves as a platform to share insights and innovative solutions in developing robust and secure AI systems that handle the unique issues brought about by foundation models, such as the high number of learnable parameters leading to edge computing and communication challenges, privacy and security concerns due to learning from a vast amount of data, and limited personalization possibilities. Through fostering collaboration and exchanging ideas, the workshop seeks to push the boundaries of current understanding and applications of federated learning in the context of foundation models, thereby propelling the advancement of AI technology in Australasia.


Keynote Talks

   

Title: Federated Machine Intelligence

Speaker: Guodogn Long, University of Technology Sydney, Australia

Biography
Dr Long joined UTS in 2010 and obtained his PhD degree from UTS in 2014. His current research interest focuses on using federated learning to develop a trustworthy AI with privacy-preserving and personalised intelligence, and also developing new on-device intelligence to cooperate with pre-trained foundation models at the serve. He has published approximately 150 papers, accumulating over 24,000 citations with an h-index of 50. In 2023, my publications received 6,376 citations. Many of my works have appeared in top-tier venues, including NeurIPS, ICLR, ICML, AAAI and IJCAI, all classified A* by CORE. He has consistently ranked among the AI 2000 Most Influential Scholars in AAAI/IJCAI (by AMiner) since 2022, achieving 21st globally in 2024.

He actively serves the AI research community, having co-chaired the Australasian Joint Conference on AI in 2021. I will continue as general co-chair for the same conference in 2025 at ANU. In addition, he is the general co-chair for The ACM Web Conference (CORE A*) in Sydney 2025, collaborating with leading Australian researchers. Since 2023, he has been co-director of the Representation Learning for Machine Intelligence (ReLMI) research lab (formerly known as DSKD lab) at UTS:AAII. He is also served as the technical theme leader for Digital, Virtual, and AI in Health at UTS, leading discussions on technological topics and contributing to joint research projects with the Faculty of Health in UTS.

   

Title: Federated Learning Research from Cybersecurity Perspective

Speaker: Xingliang Yuan, University of Melbourne, Australia

Biography
Xingliang Yuan is an Associate Professor in the School of Computing and Information Systems at the University of Melbourne. He has broad interests in computer security, including data security and privacy, secure networked systems, and trustworthy machine learning. His research has been supported by Australian Research Council, CSIRO, Australian Department of Home Affairs, Australian Department of Health and Aged Care, and Oceania Cyber Security Centre. His work has been published in major venues of computer security and systems, such as CCS, S&P, USENIX Security, NDSS, TDSC, TIFS, etc. Before joining CIS, he spent almost 7 years at Monash Faculty of IT. He is a sole recipient of the Dean's Award for Excellence in Research by an Early Career Researcher (2020), and the Faculty Teaching Excellence Award (2021) at Monash. He is a co-recipient of the best paper award in the European Symposium on Research in Computer Security (ESORICS) 2021. He is currently on the editorial board of IEEE Transactions on Dependable and Secure Computing (TDSC) and IEEE Transactions on Service Computing (TSC). He served as a track co-chair of ICDCS'24, WISE'24, and a program co-chair of Lamps@CCS'24, SecTL@AsiaCCS'23, and NSS'22.

   

Title: Challenges and Opportunities for Federated Learning in the Age of Foundation Models

Speaker: Han Yu, Associate Professor, Nanyang Technological University, Singapore

Biography
Han Yu is a tenured Associate Professor in the College of Computing and Data Science (CCDS), Nanyang Technological University (NTU), Singapore. Between 2018 and 2024, he was a Nanyang Assistant Professor (NAP) in CCDS, NTU. He has been a Visiting Scholar at the Department of Computer Science and Engineering, Hong Kong University of Science and Technology (HKUST) from 2017 to 2018. Between 2015 and 2018, he held the prestigious Lee Kuan Yew Post-Doctoral Fellowship (LKY PDF). His work focuses on trustworthy federated learning. He has published over 300 research papers in leading international conferences (e.g., AAAI, AAMAS, ACM MM, CIKM, CVPR, ECAI, EMNLP, ICASSP, ICME, ICML, ICWS, IJCAI, INFOCOM, NAACL, NeurIPS, SIGIR, SIGMOD, WWW), journals (e.g., PIEEE, TII, TIST, TKDE, TNNLS) and book chapters. He co-authored the book Federated Learning - the first monograph on the topic of federated learning. His research work has been recognized with multiple scientific awards. In 2021, he co-founded the Trustworthy Federated Ubiquitous Learning (TrustFUL) Research Lab. He is an Associate Editor of IEEE TNNLS, IJCAI Sponsorship Officer General, WWW'25 Sponsorship Co-Chair, and Vice Chair of the IEEE Computational Intelligence Society (CIS) Standards Committee. He is a Distinguished Member of CCF, and a Senior Member of AAAI and IEEE. For his continued contributions to the field of trustworthy AI and real-world impact in the society, he has been identified as one of the World's Top 2% Scientists in AI, and selected as one of the JCI Ten Outstanding Young Persons (TOYP) of Singapore.


Co-Chairs


Organized by