论文标题
具有多个已知群集的个性化联合学习
Personalized Federated Learning with Multiple Known Clusters
论文作者
论文摘要
当用户内有已知的群集结构时，我们会考虑个性化联合学习的问题。直观的方法是将参数正规化，以便相同群集中的用户共享相似的模型权重。然后可以将群集之间的距离正规化，以反映用户不同群集之间的相似性。我们开发了一种算法，该算法允许每个群集独立通信并得出收敛结果。我们研究了一个层次线性模型，从理论上讲，我们的方法的表现优于独立学习的代理，而代理人学习了单一的共享权重。最后，我们使用模拟和现实世界数据证明了方法的优势。
We consider the problem of personalized federated learning when there are known cluster structures within users. An intuitive approach would be to regularize the parameters so that users in the same cluster share similar model weights. The distances between the clusters can then be regularized to reflect the similarity between different clusters of users. We develop an algorithm that allows each cluster to communicate independently and derive the convergence results. We study a hierarchical linear model to theoretically demonstrate that our approach outperforms agents learning independently and agents learning a single shared weight. Finally, we demonstrate the advantages of our approach using both simulated and real-world data.
