Peter Kairouz, Marco Gruteser, & Ewa Dominowska

Dan Ramage, Brendan McMahan, & Kallista Bonawitz

Martin Jaggi, EPFL

Track 1 - Session Chair: Adria Gascon (Privacy & Security) | Track 1 Google Meet Link
1. Zheng Xu - Practical and Private Federated Learning without Sampling or Shuffling  
2. Albert Cheu - Shuffle Private Vector Summation
3. Bo Li - Certifiably Robust Federated Learning against Poisoning Attacks
4. Borja Balle - Reconstructing Training Data with Informed Adversaries
5. Amir Houmansadr - A Critical Evaluation of Poisoning Attacks on Federated Learning
6. Hamed Haddadi - PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments  
7. Suhas Diggavi - Privacy-performance trade-offs in the Shuffled Model of Federated Learning  

8 Phillipp Schopmann -- Distributed Point Functions

Track 2 - Session Chair: Shanshan Wu (Federated Optimization & Analytics) | Track 2 Google Meet Link
1. Peter Richtarik - EF21: A new, simpler, theoretically better, and practically faster error feedback
2. Zach Charles - On Large-Cohort Training for Federated Learning
3. Gauri Joshi - Leveraging Spatial and Temporal Correlations in Sparsified Mean Estimation
4. Nicolas Lane - Scaling and Accelerating Federated Learning Research with Flower
5. Andrew Hard - Mixing Federated and Centralized Training
6.Ayfer Ozgur - From worst-case to pointwise bounds for distributed estimation under communication constraints
7. Walid Saad - Distributed Learning and Wireless Networks: A Closer Union

8. Phillip Gibbons - Federated Learning under Distributed Concept Drift

Rachel Cummings, Columbia University

Peter Kairouz & Marco Gruteser

Adam Smith, Boston University

Track 1 - Session Chair: Zachary Garrett (Privacy & Security) | Track 1 Google Meet Link
1. Andreas Haeberlen - Privacy-Preserving Federated Analytics with Billions of Users
2. Li Xiong - Federated Learning with Heterogeneous Data and Heterogeneous Differential Privacy
3. Dawn Song - Federated frequency moments estimation and its application in feature selection
4. Florian Tramer - Better Membership Inference Attacks
5. Shuang Song - Public Data-Assisted Mirror Descent for Private Model Training
6. Steven Wu - Private Multi-Task Learning: Formulation and Applications to Federated Learning 
7.  Satyen Kale - Learning with user-level differential privacy

Track 2 - Session Chair: Sean Augenstein (Federated Optimization & Analytics) | Track 2 Google Meet Link 
1. Athina Markopoulou - Location Leakage in Federated Signal Maps
2. Eugene Bagdasaryan - Federated Analytics: Building Location Heatmaps under Distributed Differential Privacy with Secure Aggregation
3. Jae Hun Ro - FedJAX: Federated Learning Simulation with JAX
4. Giulia Fanti - Reducing the Communication Cost of Federated Learning through Multistage Optimization
5. Ankit Rawat - FedLite: A Scalable Approach for Federated Learning on Resource-constrained Clients
6. Yang Liu - Federated Learning of Larger Server Models via Selective Knowledge Fusion
7. Marco Canini - Resource-Efficient Federated Learning

Hubert Eichner, Francoise Beaufay, Ravi Kumar & Peter Kairouz

Mosharaf Chowdhury, University of Michigan

To view this schedule please visit the Day 3 event page:
Workshop on Federated Learning and Analytics Research using TFF