Timezone: »

International Workshop on Scalability, Privacy, and Security in Federated Learning (SpicyFL 2020)
Xiaolin Andy Li · Dejing Dou · Ameet Talwalkar · Hongyu Li · Jianzong Wang · Yanzhi Wang

Sat Dec 12 08:20 AM -- 07:10 PM (PST) @ None
Event URL: http://icfl.cc/SpicyFL/2020 »

In the recent decade, we have witnessed rapid progress in machine learning in general and deep learning in particular, mostly driven by tremendous data. As these intelligent algorithms, systems, and applications are deployed in real-world scenarios, we are now facing new challenges, such as scalability, security, privacy, trust, cost, regulation, and environmental and societal impacts. In the meantime, data privacy and ownership has become more and more critical in many domains, such as finance, health, government, and social networks. Federated learning (FL) has emerged to address data privacy issues. To make FL practically scalable, useful, efficient, and effective on security and privacy mechanisms and policies, it calls for joint efforts from the community, academia, and industry. More challenges, interplays, and tradeoffs in scalability, privacy, and security need to be investigated in a more holistic and comprehensive manner by the community. We are expecting broader, deeper, and greater evolution of these concepts and technologies, and confluence towards holistic trustworthy AI ecosystems.

This workshop provides an open forum for researchers, practitioners, and system builders to exchange ideas, discuss, and shape roadmaps towards scalable and privacy-preserving federated learning in particular, and scalable and trustworthy AI ecosystems in general.

Sat 8:20 a.m. - 8:30 a.m.

Introductory comments by the organizers.

Xiaolin Andy Li
Sat 8:30 a.m. - 9:00 a.m.
Keynote Talk 1: Dawn Song
Sat 9:00 a.m. - 9:15 a.m.
A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning, Samuel Horváth and Peter Richtárik (Contributed Talk)
Sat 9:15 a.m. - 9:30 a.m.
Backdoor Attacks on Federated Meta-Learning, Chien-Lun Chen, Leana Golubchik and Marco Paolieri (Contributed Talk)
Sat 9:30 a.m. - 9:45 a.m.
FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning, Hong-You Chen and Wei-Lun Chao (Contributed Talk)
Sat 9:45 a.m. - 10:00 a.m.
Preventing Backdoors in Federated Learningby Adjusting Server-side Learning Rate, Mustafa Ozdayi, Murat Kantarcioglu and Yulia Gel (Contributed Talk)
Sat 10:00 a.m. - 10:30 a.m.
Keynote Talk 2: H. Brendan McMahan
Sat 10:30 a.m. - 10:50 a.m.
Lightning Talk Session 1: 10 papers, 2m each (Lightning Talk Session 1)
Sat 10:50 a.m. - 11:20 a.m.
Keynote Talk 3: Ruslan Salakhutdinov
Sat 11:20 a.m. - 11:35 a.m.

Chaoyang He, Songze Li, Jinhyun So, Mi Zhang, Xiao Zeng, Hongyi Wang, Xiaoyang Wang, Praneeth Vepakomma, Abhishek Singh, Hang Qiu, Xinghua Zhu, Jianzong Wang, Li Shen, Peilin Zhao, Yan Kang, Yang Liu, Ramesh Raskar, Qiang Yang, Murali Annavaram and Salman Avestimehr

Sat 11:35 a.m. - 11:50 a.m.
Learning to Attack Distributionally Robust Federated Learning, Wen Shen, Henger Li and Zizhan Zheng (Contributed Talk)
Sat 11:50 a.m. - 12:20 p.m.
Keynote Talk 4: Virginia Smith
Sat 12:20 p.m. - 12:36 p.m.
Lightning Talk Session 2: 8 papers, 2m each (Lightning Talk Session 2)
Sat 12:36 p.m. - 1:30 p.m.
Poster Session 1
Sat 1:30 p.m. - 2:00 p.m.
Keynote Talk 5: John C. Duchi
Sat 2:00 p.m. - 2:15 p.m.
On Biased Compression for Distributed Learning, Aleksandr Beznosikov, Samuel Horváth, Mher Safaryan and Peter Richtarik (Contributed Talk)
Sat 2:15 p.m. - 2:30 p.m.
PAC Identifiability in Federated Personalization, Ben London (Contributed Talk)
Sat 2:30 p.m. - 2:45 p.m.
Model Pruning Enables Efficient Federated Learning on Edge Devices, Yuang Jiang, Shiqiang Wang, Victor Valls, Bong Jun Ko, Wei-Han Lee, Kin Leung and Leandros Tassiulas (Contributed Talk)
Sat 2:45 p.m. - 3:00 p.m.
Hybrid FL: Algorithms and Implementation, Xinwei Zhang, Tianyi Chen, Mingyi Hong and Wotao Yin (Contributed Talk)
Sat 3:00 p.m. - 3:30 p.m.
Sat 3:30 p.m. - 4:00 p.m.
Keynote Talk 6: Tao Yang
Sat 4:00 p.m. - 4:20 p.m.
Lightning Talk Session 3: 10 papers, 2m each (Lightning Talk Session 3)
Sat 4:20 p.m. - 4:50 p.m.
Keynote Talk 7: Tong Zhang
Sat 4:50 p.m. - 5:00 p.m.
Lightning Talk Session 4: 5 papers, 2m each (Lightning Talk Session 4)
Sat 5:00 p.m. - 6:00 p.m.
Panel Discussion
Sat 6:00 p.m. - 7:00 p.m.
Poster Session 2 (Papers presented in the afternoon)
Sat 7:00 p.m. - 7:10 p.m.

Comments by the organizers

Xiaolin Andy Li

Author Information

Xiaolin Andy Li (Cognization Lab)

Dr. Xiaolin Andy Li is a Partner and VP of Tongdun Technology, heading the AI Institute. As a part of the AI Institute, the Cognization Lab is located at Palo Alto Square, near Stanford University. Dr. Xiaolin Andy Li was a tenured Full Professor and University Term Professor in Computer Engineering at the University of Florida. As the founding center director, he founded NSF Center for Big Learning (CBL) with UF, CMU, UMKC and U. Oregon and three dozens of leading companies as industry members, the first national center on deep learning in USA. He was also the director of Large-scale Intelligent Systems Laboratory (Li Lab). His research interests include machine learning/deep learning, intelligent platform, cloud computing, Internet-of-Things, security & privacy, financial technology, precision medicine, and logistics. He led the design and deployment of one of the first software-defined 100G campus research networks and campus clouds GatorCloud, the best campus research network in the nation. His team designed and developed many platforms and tools, such as DeepCloud, CognitiveEngine, DeepEyes, OneTask, DeepSLAM, CloudBay, SMART, GemsCloud, Guoguo, FindingNemo, ToGathor, DeepDDoS, DeepMalware, S3PAS, FoldingZero, PrimateAI, MySurgeryRisk and DeepDrug. He received the NSF CAREER Award, the Internet2 Innovative Application Award, NSF I-Corps Top Team Award, Top Team Award (DeepBipolar) in the CAGI Challenge, and Best Paper Awards (IEEE ICMLA 2016, IEEE SECON 2016, ACM CAC 2013, and IEEE UbiSafe 2007). He has published over 150 peer-reviewed papers and dozens of patent applications. He received PhD in Computer Engineering from Rutgers University.

Dejing Dou (" University of Oregon, USA")
Ameet Talwalkar (CMU)
Hongyu Li (tongdun)
Jianzong Wang (Ping An Technology (Shenzhen) Co., Ltd)
Yanzhi Wang (Northeastern University)

More from the Same Authors