Skip to contentSkip to filters

We use cookies for analytics.

The Many Faces of Heterogeneity: Federated, Continual, and Modular Learning

Marco Ciccone

Vector Institute

Recording

35 min

Abstract

Marco Ciccone connects client drift in federated learning, forgetting across time, and unreliable composition of independently trained modules. These settings each require a system to learn from heterogeneous sources while preserving or combining useful knowledge. The talk shows where methods from one setting can inform the others and outlines questions for designing around heterogeneity.

Topics