论文标题
图形辅助沟通高效的合奏联合学习
Graph-Assisted Communication-Efficient Ensemble Federated Learning
论文作者
论文摘要
由于沟通带宽有限，沟通效率是联合学习的必要条件。为此，本文开发了一个算法框架，其中学习了预培训模型的合奏。在每个学习回合中，服务器都会根据图的结构选择一个预训练模型的子集来构建集成模型，该结构表征了服务器对模型的信心。然后，只有选定的模型传输给客户，以免违反某些预算限制。从客户端接收更新后，服务器会相应地完善图表的结构。事实证明，拟议的算法可以享受次线性遗憾。实际数据集的实验证明了我们新方法的有效性。
Communication efficiency arises as a necessity in federated learning due to limited communication bandwidth. To this end, the present paper develops an algorithmic framework where an ensemble of pre-trained models is learned. At each learning round, the server selects a subset of pre-trained models to construct the ensemble model based on the structure of a graph, which characterizes the server's confidence in the models. Then only the selected models are transmitted to the clients, such that certain budget constraints are not violated. Upon receiving updates from the clients, the server refines the structure of the graph accordingly. The proposed algorithm is proved to enjoy sub-linear regret bound. Experiments on real datasets demonstrate the effectiveness of our novel approach.
