FedEmbed: Personalized Private Federated Learning
This addresses the challenge of personalizing federated learning with privacy guarantees for users with diverse preferences, though it appears incremental as it builds on existing federated and private learning methods.
The paper tackles the problem of handling conflicting labels in personalized private federated learning by introducing FedEmbed, which uses sub-populations of similar users and personal embeddings, achieving up to 45% improvement over baseline approaches.
Federated learning enables the deployment of machine learning to problems for which centralized data collection is impractical. Adding differential privacy guarantees bounds on privacy while data are contributed to a global model. Adding personalization to federated learning introduces new challenges as we must account for preferences of individual users, where a data sample could have conflicting labels because one sub-population of users might view an input positively, but other sub-populations view the same input negatively. We present FedEmbed, a new approach to private federated learning for personalizing a global model that uses (1) sub-populations of similar users, and (2) personal embeddings. We demonstrate that current approaches to federated learning are inadequate for handling data with conflicting labels, and we show that FedEmbed achieves up to 45% improvement over baseline approaches to personalized private federated learning.