Antonious M. Girgis
Antonious M. Girgis is a Staff Research Scientist at Google DeepMind, working on Personal Intelligence in Gemini and memory architectures for AI agents. Previously, he contributed to multimodal and audio post-training for Gemini Live. He received his Ph.D. in Electrical and Computer Engineering from UCLA, M.Sc. from Nile University, and B.Sc. from Cairo University. His honors include the 2021 ACM CCS Best Paper Award, the UCLA ECE Distinguished Ph.D. Dissertation Award, and the 2022 Amazon Ph.D. Fellowship. His research spans AI agent memory, personalization, multimodal foundation models, differential privacy, federated learning, and information theory.
Research Areas
Authored Publications
Sort By
Learning from straggler clients in federated learning
Ehsan Amid
Rohan Anil
Arxiv (2024) (to appear)
Preview abstract
How well do existing federated learning algorithms learn from client devices that return model updates with a significant time delay? Is it even possible to learn effectively from clients that report back minutes, hours, or days after being scheduled? We answer these questions by developing Monte Carlo simulations of client latency that are guided by real-world applications. We compare well-known synchronous optimization algorithms like FedAvg and FedAdam with the state-of-the-art asynchronous FedBuff algorithm, and discover that these existing approaches often struggle to learn from severely delayed clients. To improve upon these, we experiment with modifications including distillation regularization and exponential moving averages of model weights. Finally, we invent two new algorithms, FARe-DUST and FeAST-on-MSG, based on distillation and averaging, respectively. Experiments with the EMNIST, CIFAR-100, and StackOverflow benchmark federated learning tasks demonstrate that our new algorithms outperform existing ones in terms of accuracy for straggler clients, while also providing better trade-offs between training time and total accuracy.
View details
