Federated Distillation Methodology for Label-Based Group Structures

In federated learning (FL), clients train models locally without sharing raw data, ensuring data privacy. In particular, federated distillation transfers knowledge to clients regardless of the model architecture. However, when groups of clients with different label distributions exist, sharing the s...

Disgrifiad llawn

Manylion Llyfryddiaeth
Prif Awduron: Geonhee Yang, Hyunchul Tae
Fformat: Erthygl
Iaith:English
Cyhoeddwyd: MDPI AG 2023-12-01
Cyfres:Applied Sciences
Pynciau:
Mynediad Ar-lein:https://www.mdpi.com/2076-3417/14/1/277