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).
@article{arxiv.2409.02064,
title = {Your Data, My Model: Learning Who Really Helps in Federated Learning},
author = {Shamsiiat Abdurakhmanova and Amirhossein Mohammadi and Yasmin SarcheshmehPour and Alexander Jung},
journal= {arXiv preprint arXiv:2409.02064},
year = {2025}
}