Federated Kernelized Multi-Task Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Central Server Free Federated Learning over Single-sided Trust Social Networks (2019, background): “To address both statistical and system challenges, Smith et al. (2017b) and Caldas et al. (2018) propose a multi-task learning framework for federated learning and its related optimization algorithm, which extends early works SDCA (Shalev-Shwartz and Zhang, 2013; Yang, 2013; Yang et al., 2013) and…”
Edge Learning for B5G Networks With Distributed Signal Processing: Semantic Communication, Edge Computing, and Wireless Sensing (2022, unknown): “A growing body of recent researches, e.g., [14], [50], [58], [63], [64], [65], [66], [67], [68], [69], have developed effective methods to deal with these challenges.”
Federated User Representation Learning (2019, background): “…user i , the gradient of the local loss function with respect to other users’ private parameters is zero: Equation 1 is satisﬁed by most implementations of personalization techniques like collaborative ﬁltering, personalization via user embeddings or user-speciﬁc model weights, and MTL-FL [28, 27].”
Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking Systems (2021, background): “In [61], the authors improve upon MOCHA [60] through incorporating non-linear mappings into the design of multi-task federated learning.”