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.
| Opening Remarks | |
| Keynote Talk 1: Dawn Song | |
| A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning, Samuel Horváth and Peter Richtárik (Contributed Talk) | |
| Backdoor Attacks on Federated Meta-Learning, Chien-Lun Chen, Leana Golubchik and Marco Paolieri (Contributed Talk) | |
| FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning, Hong-You Chen and Wei-Lun Chao (Contributed Talk) | |
| Preventing Backdoors in Federated Learningby Adjusting Server-side Learning Rate, Mustafa Ozdayi, Murat Kantarcioglu and Yulia Gel (Contributed Talk) | |
| Keynote Talk 2: H. Brendan McMahan | |
| Lightning Talk Session 1: 10 papers, 2m each (Lightning Talk Session 1) | |
| Keynote Talk 3: Ruslan Salakhutdinov | |
| FedML: A Research Library and Benchmark for Federated Machine Learning, Chaoyang He, et. al. (Contributed Talk) | |
| Learning to Attack Distributionally Robust Federated Learning, Wen Shen, Henger Li and Zizhan Zheng (Contributed Talk) | |
| Keynote Talk 4: Virginia Smith | |
| Lightning Talk Session 2: 8 papers, 2m each (Lightning Talk Session 2) | |
| Poster Session 1 | |
| Keynote Talk 5: John C. Duchi | |
| On Biased Compression for Distributed Learning, Aleksandr Beznosikov, Samuel Horváth, Mher Safaryan and Peter Richtarik (Contributed Talk) | |
| PAC Identifiability in Federated Personalization, Ben London (Contributed Talk) | |
| 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) | |
| Hybrid FL: Algorithms and Implementation, Xinwei Zhang, Tianyi Chen, Mingyi Hong and Wotao Yin (Contributed Talk) | |
| Break | |
| Keynote Talk 6: Tao Yang | |
| Lightning Talk Session 3: 10 papers, 2m each (Lightning Talk Session 3) | |
| Keynote Talk 7: Tong Zhang | |
| Lightning Talk Session 4: 5 papers, 2m each (Lightning Talk Session 4) | |
| Panel Discussion | |
| Poster Session 2 (Papers presented in the afternoon) | |
| Closing Remarks (Talk) | |