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.

翻译：摘要：联邦学习（FL）面临的核心挑战之一是统计异质性，这削弱了全局模型在各客户端上的泛化能力。为解决该问题，我们提出了一种名为自适应本地聚合联邦学习（FedALA）的方法，通过从全局模型中捕获客户端模型所需的个性化信息，实现个性化联邦学习。FedALA的关键组件是自适应本地聚合（ALA）模块，该模块可在每轮迭代训练前，根据各客户端的本地目标，自适应地聚合下载的全局模型与本地模型，从而初始化本地模型。为验证FedALA的有效性，我们在计算机视觉和自然语言处理领域的五个基准数据集上进行了广泛实验。FedALA在测试准确率上最多可比11种最先进基线方法提升3.27%。此外，我们将ALA模块应用于其他联邦学习方法，最高可实现24.19%的测试准确率提升。