Personalized Progressive Federated Learning with Leveraging Client-Specific Vertical Features


Tae Hyun Kim, Won Seok Jang, Sun Cheol Heo, MinDong Sung, and Yu Rang Park, Yonsei University College of Medicine, South Korea


Federated learning (FL) has been used for model building across distributed clients. However, FL cannot leverage vertically partitioned features to increase the model complexity. In this study, we proposed a personalized progressive federated learning (PPFL) model, which is a multimodel PFL approach that allows the leveraging of vertically partitioned client-specific features. The performance of PPFL was evaluated using the Physionet Challenges 2012 dataset. We compared the performance of in-hospital mortality and length of stay prediction between our model and the FedAvg, FedProx, and local models. The PPFL showed an accuracy of 0.849 and AUROC of 0.790 in average in hospital mor-tality prediction, which are the highest scores compared to client-specific algorithm. For length-of-stay prediction, PPFL also showed an AUROC of 0.808 in average which was the highest among all comparators.


Personalized Federated Learning, Vertical Federated Learning, Non-IID data.

Full Text  Volume 13, Number 1