-
8:30 AM - 8:40 AM (PDT)
Chairs' opening remarks
-
8:40 AM - 9:25 AM
Efficient Distributed Learning via Independent
Subnet Training: Results and Trends
Speaker: Dr. Anastasios Kyrillidis, Rice University, USA (remote)
-
9:30 AM - 10:15 AM
Machine Learning and the
Data Center: A Dangerous Dead End
Speaker: Dr. Nicholas Lane, University of Cambridge & Samsung AI, UK (remote)
-
10:15 AM - 10:30 AM
Break
-
10:30 AM - 11:15 AM
Knowledge Transfer Federated Learning
Speaker: Dr. Yang Liu, Tsinghua University, China (in-person)
-
11:20 AM - 12:05 PM
Where to Begin? On the Impact of Pre-training and
Initialization in Federated Learning
Speaker: Dr. Michael Rabbat, Meta AI, Canada (in-person)
-
12:05 PM - 1:30 PM
Lunch break
-
1:30 PM - 2:15 PM
Heterogeneity-aware Algorithms
for Federated Optimization
Speaker: Dr. Gauri Joshi, Carnegie Mellon University, USA (in-person)
-
2:20 PM - 3:05 PM
Certifiable Trustworthy Federated Learning:
Robustness, Privacy, Generalization, and
Their Interconnections
Speaker: Dr. Bo Li, University of Illinois at Urbana-Champaign, USA (remote)
-
3:05 PM - 3:30 PM
Break
-
3:30 PM - 5:00 PM
Oral session
-
(3:30 - 3:45 PM)
OpenFed: A Comprehensive and Versatile Open-Source Federated Learning Framework
-
(3:45 - 4:00 PM)
Federated Learning in Non-IID Settings Aided by Differentially Private Synthetic Data
-
(4:00 - 4:15 PM)
Many-Task Federated Learning: A New Problem Setting and A Simple Baseline
-
(4:15 - 4:30 PM)
Mixed Quantization Enabled Federated Learning to Tackle Gradient Inversion Attacks
-
(4:30 - 4:45 PM)
Asynchronous Federated Continual Learning
-
(4:45 - 5:00 PM)
TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Training