English

A Generalized Meta Federated Learning Framework with Theoretical Convergence Guarantees

Machine Learning 2025-05-14 v2

Abstract

Meta federated learning (FL) is a personalized variant of FL, where multiple agents collaborate on training an initial shared model without exchanging raw data samples. The initial model should be trained in a way that current or new agents can easily adapt it to their local datasets after one or a few fine-tuning steps, thus improving the model personalization. Conventional meta FL approaches minimize the average loss of agents on the local models obtained after one step of fine-tuning. In practice, agents may need to apply several fine-tuning steps to adapt the global model to their local data, especially under highly heterogeneous data distributions across agents. To this end, we present a generalized framework for the meta FL by minimizing the average loss of agents on their local model after any arbitrary number ν\nu of fine-tuning steps. For this generalized framework, we present a variant of the well-known federated averaging (FedAvg) algorithm and conduct a comprehensive theoretical convergence analysis to characterize the convergence speed as well as behavior of the meta loss functions in both the exact and approximated cases. Our experiments on real-world datasets demonstrate superior accuracy and faster convergence for the proposed scheme compared to conventional approaches.

Keywords

Cite

@article{arxiv.2504.21327,
  title  = {A Generalized Meta Federated Learning Framework with Theoretical Convergence Guarantees},
  author = {Mohammad Vahid Jamali and Hamid Saber and Jung Hyun Bae},
  journal= {arXiv preprint arXiv:2504.21327},
  year   = {2025}
}
R2 v1 2026-06-28T23:16:17.139Z