Your Data, My Model: Learning Who Really Helps in Federated Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908383087427584 |
|---|---|
| author | Abdurakhmanova, Shamsiiat Mohammadi, Amirhossein SarcheshmehPour, Yasmin Jung, Alexander |
| author_facet | Abdurakhmanova, Shamsiiat Mohammadi, Amirhossein SarcheshmehPour, Yasmin Jung, Alexander |
| contents | Many important machine learning applications involve networks of devices-such as wearables or smartphones-that generate local data and train personalized models. A key challenge is determining which peers are most beneficial for collaboration. We propose a simple and privacy-preserving method to select relevant collaborators by evaluating how much a model improves after a single gradient step using another devices data-without sharing raw data. This method naturally extends to non-parametric models by replacing the gradient step with a non-parametric generalization. Our approach enables model-agnostic, data-driven peer selection for personalized federated learning (PersFL). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_02064 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Your Data, My Model: Learning Who Really Helps in Federated Learning Abdurakhmanova, Shamsiiat Mohammadi, Amirhossein SarcheshmehPour, Yasmin Jung, Alexander Machine Learning 68T05 I.2.6; I.2.11 Many important machine learning applications involve networks of devices-such as wearables or smartphones-that generate local data and train personalized models. A key challenge is determining which peers are most beneficial for collaboration. We propose a simple and privacy-preserving method to select relevant collaborators by evaluating how much a model improves after a single gradient step using another devices data-without sharing raw data. This method naturally extends to non-parametric models by replacing the gradient step with a non-parametric generalization. Our approach enables model-agnostic, data-driven peer selection for personalized federated learning (PersFL). |
| title | Your Data, My Model: Learning Who Really Helps in Federated Learning |
| topic | Machine Learning 68T05 I.2.6; I.2.11 |
| url | https://arxiv.org/abs/2409.02064 |