Workshop on Federated Learning and Analytics (FL-IBM’20)

February 6, 2020
IBM Thomas J Watson Research Center
1101 Kitchawan Road, Yorktown Heights, NY 10598
IBM YKT logo

How to attend remotely?

For the people who are affected by this unexpected event of 2019 Novel Coronavirus (2019-nCoV) Outbreak, we are providing the way for everyone to attend remotely. Please use this webex link ( IBM FL Workshop) for attending the workshop on 02/06/2020!


Workshop Program

Time Title Speakers
10:00-10:15am Opening Remarks Bijan Davari (IBM Fellow/Vice President of IBM Research)
10:15-10:45pm Invited Talk 1: Federated Learning in Resource-Constrained Edge Computing Systems Shiqiang Wang, IBM Research, USA
10:45-11:15pm Invited Talk 2: Efficient and Accurate Approaches for Privacy-Preserving Federated Learning Nathalie Baracaldo, IBM Research, USA
11:15-11:30pm Coffee Break
11:30-12:00pm Invited Talk 3: Analyzing Federated Learning Through An Adversarial Lens Supriyo Chakraborty, IBM Research, USA
12:00-13:00pm Lunch Break (Provided)
13:00-13:30pm Invited Talk 4: Vertical(cross-silo) federated learning : some concepts and applications Yang Liu (on behalf of Qiang Yang), Hong Kong University of Science and Technology and WeBank CAO, China
13:30-14:00pm Invited Talk 5: Federated learning at Google: systems, algorithms, and applications Keith Bonawitz, Google Research, USA
14:00-14:30pm Invited Talk 6: Split Learning: A new resource efficient alternative for distributed machine learning Praneeth Vepakomma (on behalf of Ramesh Raskar), Massachusetts Institute of Technology, USA
14:30-15:00pm Invited Talk 7: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Data Mingyi Hong, University of Minnesota, USA
15:00-15:15pm Coffee Break
15:15-15:45pm Invited Talk 8: Incentives for Federated Learning Boi Faltings, Swiss Federal Institute of Technology Lausanne, Switzerland
15:45-16:15pm Invited Talk 9: Bayesian Nonparametric Fusion of heterogeneous models Mikhail Yurochkin, IBM Research, USA
16:15-17:15pm Panel: Data Privacy and Regulatory Issues in AI: Enterprise and Customer Perspectives Shahrokh Daijavad, Qiang Yang, Keith Bonawitz, Ramesh Raskar, Shiqiang Wang


Privacy and security have become critical concerns in recent years, particularly as companies and organizations increasingly collect detailed information about their products and users. This information can enable machine learning methods that produce better products. However, it also has the potential to allow for misuse, especially when private data about individuals is involved. Recent research shows that privacy and utility do not necessarily need to be at odds, but can be addressed by careful design and analysis. The need for such research is reinforced by the recent introduction of new legal constraints, led by the European Union’s General Data Protection Regulation (GDPR), which is already inspiring novel legislative approaches around the world such as Cyber-security Law of the People’s Republic of China and The California Consumer Privacy Act of 2018.

An approach that has the potential to address a number of problems in this space is Federated Learning (FL). FL is an ML setting where many clients (e.g., mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g., service provider), while keeping the training data decentralized. Organizations and mobile devices have access to increasing amounts of sensitive data, with scrutiny of ML privacy and data handling practices increasing correspondingly. These trends have produced significant interest in FL, since it provides a viable path to state-of-the-art ML without the need for the centralized collection of training data – and the risks and responsibilities that come with such centralization. Nevertheless, significant challenges remain open in the FL setting, the solution of which will require novel techniques from multiple fields, as well as improved open-source tooling for both FL research and real-world deployment.

This one-day workshop aims to bring together both academic researchers and industrial practitioners from different backgrounds and perspectives to address above challenges. The workshop will consist of 12 invited talks on a wide variety of methods and applications. This workshop intends to share visions of investigating new approaches, methods, and systems at the intersection of Federated Learning and real-world applications.

Topics of interest (including but not limited to)

The invited talks will cover innovative research and applications around the topics below. These talks introduce new theoretical concepts or methods, help to develop a better understanding of new emerging concepts through extensive experiments, or demonstrate a novel application of these methods to a domain.

And with particular focuses but not limited to these application domains:

Important Information

Invited Speakers

Workshop Co-Chairs

Organizing Committee