• 

  Jianwei Huang

  Vice President at 优德官网; Presidential Chair Professor at The Chinese University of Hong Kong, Shenzhen

  Executive Chair

  Bio

  Abstract
• 

  Bing Luo

  优德官网-Yale Joint Postdoc Researcher

  Co Chair

  Bio

  Abstract
• 

  Leandros Tassiulas

  John C. Malone Professor of Electrical Engineering at Yale University

  Efficient federated learning in synchronous and spiking neural networks

  Bio

  Leandros Tassiulas is the John C. Malone Professor of Electrical Engineering at Yale University. His research interests are in the field of computer and communication networks with emphasis on fundamental mathematical models and algorithms of complex networks, architectures and protocols of wireless systems, sensor networks, novel internet architectures and experimental platforms for network research. His most notable contributions include the max-weight scheduling algorithm and the back-pressure network control policy, opportunistic scheduling in wireless, the maximum lifetime approach for wireless network energy management, and the consideration of joint access control and antenna transmission management in multiple antenna wireless systems. Dr. Tassiulas is a Fellow of IEEE (2007) and of ACM (2020). His research has been recognized by several awards including the IEEE Koji Kobayashi computer and communications award (2016), the ACM SIGMETRICS achievement award 2020, the inaugural INFOCOM 2007 Achievement Award “for fundamental contributions to resource allocation in communication networks,” several best paper awards including the INFOCOM 1994, 2017 and Mobihoc 2016, a National Science Foundation (NSF) Research Initiation Award (1992), an NSF CAREER Award (1995), an Office of Naval Research  Young Investigator Award (1997) and a Bodossaki Foundation award (1999). He holds a Ph.D. in Electrical Engineering from the University of Maryland, College Park (1991) and a Diploma in Electrical Engineering from Aristotle University of Thessaloniki (1987). He has held faculty positions at Polytechnic University, New York, University of Maryland, College Park, University of Thessaly and University of Ioannina, Greece.

  Abstract

  Federated learning (FL) allows machine learning model training from local data collected by edge/mobile devices while preserving data privacy. A challenge in FL is that client devices usually have much more limited computation and communication resources compared to servers in a data center. We propose PruneFL—a novel FL approach with adaptive and distributed parameter pruning, which adapts the model size during FL to reduce both communication and computation overhead and minimize the overall training time, while maintaining a similar accuracy as the original model. PruneFL only improves resource efficiency of deep neural networks (DNNs) in FL. However, spiking neural networks (SNNs) emerge as promising models in FL due to their intrinsic energy efficiency. To leverage this unique attribute, we design an FL method for training SNNs, and demonstrate up to 4.3x energy efficiency. Ongoing work on effectively applying pruning to SNNs will be discussed as well.

• 

  杨强

  微众银行首席人工智能官

  可信联邦学习

  Bio

  杨强，，，，，，，加拿大皇家科学院及加拿大工程院两院院士，，，，，，，微众银行首席人工智能官，，，，，，，香港科技大学盘算机与工程系讲座教授和前系主任，，，，，，，AAAI-2021大会主席，，，，，，，国际人工智能团结会（IJCAI）理事会前主席，，，，，，，香港人工智能与机械人学会（HKSAIR）理事长，，，，，，，智能投研手艺同盟（ITL）主席，，，，，，，ACM TIST 和IEEE TRANS on BIG DATA首创主编，，，，，，，CAAI，，，，，，，AAAI，，，，，，，ACM，，，，，，，IEEE，，，，，，，AAAS等多个国际学会Fellow。。。。。。。领衔全球迁徙学习和联邦学习研究及应用，，，，，，，著作包括《迁徙学习》、《联邦学习》和《联邦学习实战》等。。。。。。。

  Abstract

  联邦学习是人工智能和隐私盘算的主要交集。。。。。。。怎样使联邦学习越发清静可信和高效是以后工业和学界关注的重点。。。。。。。我在讲座中将系统回首联邦学习的希望和挑战，，，，，，，并展望几个主要生长偏向。。。。。。。

Video Archive