通过单步梯度评估，私密选择对模型提升最有帮助的协作设备。
Your Data, My Model: Learning Who Really Helps in Federated Learning
- 用单步梯度更新衡量其他设备数据的价值，无需共享原始数据。
- 方法适用于参数与非参数模型，支持个性化联邦学习。
- 适合关注隐私保护和高效协作的联邦学习研究者。
许多重要机器学习应用涉及可穿戴设备或智能手机等设备网络，这些设备生成本地数据并训练个性化模型。关键挑战在于判断哪些同伴最值得合作。我们提出一种简单且隐私保护的方法：通过使用另一设备的数据进行一次梯度步骤后模型性能的提升程度，来评估其相关性，而无需共享原始数据。该方法可通过将梯度步骤替换为泛化操作，自然扩展至非参数模型。本方法实现了模型无关、数据驱动的个性化联邦学习（PersFL）中的同行选择。
原文摘要 · Abstract (English)
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).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。