Abstract: Federated learning is a powerful machine learning approach to privacy-preserving machine learning. In this talk, I am going to introduce the use of evolutionary algorithms for enhancing the performance of federated learning.  I’ll start with a brief introduction to evolutionary multi-objective machine learning, which is followed by a presentation of an evolutionary multi-objective federated learning algorithm for reducing communication cost and an algorithm for real-time multi-objective search of deep neural architectures based on a double sampling strategy.

 

Se desarrollará de forma online en el siguiente enlace: https://meet.google.com/bzp-rtne-juq