Federated Covariate Shift Adaptation for Missing Target Output Values
This addresses data distribution mismatches in federated settings for applications like healthcare or IoT, but it is incremental as it builds on prior covariate shift methods.
The paper tackles covariate shift adaptation in federated learning with missing target outputs by extending an existing algorithm to this framework, proposing an asymptotically unbiased risk estimate and a weighted model, with efficacy supported theoretically and empirically.
The most recent multi-source covariate shift algorithm is an efficient hyperparameter optimization algorithm for missing target output. In this paper, we extend this algorithm to the framework of federated learning. For data islands in federated learning and covariate shift adaptation, we propose the federated domain adaptation estimate of the target risk which is asymptotically unbiased with a desirable asymptotic variance property. We construct a weighted model for the target task and propose the federated covariate shift adaptation algorithm which works preferably in our setting. The efficacy of our method is justified both theoretically and empirically.