论文标题
FEDALA：适应个性化联合学习的自适应本地聚合
FedALA: Adaptive Local Aggregation for Personalized Federated Learning
论文作者
论文摘要
联合学习（FL）的一个关键挑战是统计异质性会损害每个客户对全球模型的概括。为了解决这个问题，我们提出了一种通过自适应局部聚合（FEDALA）联合学习的方法，通过在个性化FL中捕获客户模型的全球模型中的所需信息。 FedAla的关键组成部分是自适应本地聚合（ALA）模块，它可以将下载的全局模型和本地模型适应每个客户端的本地目标，以在每次迭代训练之前初始化本地模型。为了评估FedAla的有效性，我们在计算机视觉和自然语言处理域中使用五个基准数据集进行了广泛的实验。 FedAla的测试准确性高于11个最先进的基线。此外，我们还将ALA模块应用于其他联合学习方法，并提高了测试准确性高达24.19％。
A key challenge in federated learning (FL) is the statistical heterogeneity that impairs the generalization of the global model on each client. To address this, we propose a method Federated learning with Adaptive Local Aggregation (FedALA) by capturing the desired information in the global model for client models in personalized FL. The key component of FedALA is an Adaptive Local Aggregation (ALA) module, which can adaptively aggregate the downloaded global model and local model towards the local objective on each client to initialize the local model before training in each iteration. To evaluate the effectiveness of FedALA, we conduct extensive experiments with five benchmark datasets in computer vision and natural language processing domains. FedALA outperforms eleven state-of-the-art baselines by up to 3.27% in test accuracy. Furthermore, we also apply ALA module to other federated learning methods and achieve up to 24.19% improvement in test accuracy.
