Your Data, My Model: Learning Who Really Helps in Federated Learning
This addresses the problem of efficient peer selection for personalized federated learning, which is incremental as it builds on existing methods.
The paper tackles the challenge of selecting beneficial collaborators in federated learning by proposing a privacy-preserving method that evaluates model improvement after a single gradient step using another device's data, without sharing raw data, and extends to non-parametric models.
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).