Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shifts
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (11) · 12938-12946
DOI: 10.1609/aaai.v38i11.29191 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Kun Jin und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
We consider a federated learning (FL) system consisting of multiple clients and a server, where the clients aim to collaboratively learn a common decision model from their distributed data. Unlike the conventional FL framework that assumes the client's data is static, we consider scenarios where the clients' data distributions may be reshaped by the deployed decision model. In this work, we leverage the idea of distribution shift mappings in performative prediction to formalize this model-dependent data distribution shift and propose a performative FL framework. We first introduce necessary and sufficient conditions for the existence of a unique performative stable solution and characterize its distance to the performative optimal solution. Then we propose the performative FedAvg algorithm and show that it converges to the performative stable solution at a rate of O(1/T) under both full and partial participation schemes. In particular, we use novel proof techniques and show how the clients' heterogeneity influences the convergence. Numerical results validate our analysis and provide valuable insights into real-world applications.
Zitieren
APA
Jin, K., Yin, T., Chen, Z., Sun, Z., Zhang, X., Liu, Y., & Liu, M. (2024). Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shifts. Proceedings of the AAAI Conference on Artificial Intelligence, 38(11), 12938-12946. https://doi.org/10.1609/aaai.v38i11.29191
Vancouver
Jin K, Yin T, Chen Z, Sun Z, Zhang X, Liu Y, et al. Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shifts. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(11):12938-12946. doi:10.1609/aaai.v38i11.29191
BibTeX
@article{Jin2024,
author = {Jin, Kun and Yin, Tongxin and Chen, Zhongzhu and Sun, Zeyu and Zhang, Xueru and Liu, Yang and Liu, Mingyan},
title = {Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shifts},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {11},
pages = {12938--12946},
doi = {10.1609/aaai.v38i11.29191}
}
EUVIMED