Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2504.21327 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913833650487296 |
|---|---|
| author | Jamali, Mohammad Vahid Saber, Hamid Bae, Jung Hyun |
| author_facet | Jamali, Mohammad Vahid Saber, Hamid Bae, Jung Hyun |
| contents | 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 $ν$ 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_21327 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Generalized Meta Federated Learning Framework with Theoretical Convergence Guarantees Jamali, Mohammad Vahid Saber, Hamid Bae, Jung Hyun Machine Learning 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 $ν$ 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. |
| title | A Generalized Meta Federated Learning Framework with Theoretical Convergence Guarantees |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2504.21327 |