Personalized Federated Multi-Task Learning over Wireless Fading Channels

Personalized Federated Multi-Task Learning over Wireless Fading Channels

Multi-task learning (MTL) is a paradigm to learn multiple tasks simultaneously by utilizing a shared network, in which a distinct header network is further tailored for fine-tuning for each distinct task. Personalized federated learning (PFL) can be achieved through MTL in the context of federated l...

Full description

Bibliographic Details
Main Authors: Matin Mortaheb, Cemil Vahapoglu, Sennur Ulukus
Format: Article
Language:English
Published: MDPI AG 2022-11-01
Series:Algorithms
Subjects:
multi-task learning
dynamic weighting
federated learning
personalized federated learning
hierarchical federated learning
over-the-air aggregation
Online Access:https://www.mdpi.com/1999-4893/15/11/421

Internet

https://www.mdpi.com/1999-4893/15/11/421

Similar Items