Efficiently aggregating trained neural networks from local clients into a
global model on a server is a widely researched topic in federated learning.
Recently, motivated by diminishing privacy concerns, mitigating potential
attacks, and reducing the overhead of communication, one-shot federated
learning (i.e., limiting client-server communication into a single round) has
gained popularity among researchers. However, the one-shot aggregation
performances are sensitively affected by the non-identical training data
distribution, which exhibits high statistical heterogeneity in some real-world
scenarios. To address this issue, we propose a novel one-shot aggregation
method with Layer-wise Posterior Aggregation, named FedLPA. FedLPA aggregates
local models to obtain a more accurate global model without requiring extra
auxiliary datasets or exposing any confidential local information, e.g., label
distributions. To effectively capture the statistics maintained in the biased
local datasets in the practical non-IID scenario, we efficiently infer the
posteriors of each layer in each local model using layer-wise Laplace
approximation and aggregate them to train the global parameters. Extensive
experimental results demonstrate that FedLPA significantly improves learning
performance over state-of-the-art methods across several metrics.

通过一次性聚合方法（One-shot Aggregation）并引入分层后验聚合（Layer-wise Posterior Aggregation）的新方法 FedLPA，实现在其他机器学习领域中每一层的数据的继承和共享，从而显著提升了该方法的学习性能。