We tackle a major challenge in federated learning (FL) -- achieving good
performance under highly heterogeneous client distributions. The difficulty
partially arises from two seemingly contradictory goals: learning a common
model by aggregating the information from clients, and learning local
personalized models that should be adapted to each local distribution. In this
work, we propose Solution Simplex Clustered Federated Learning (SosicFL) for
dissolving such contradiction. Based on the recent ideas of learning solution
simplices, SosicFL assigns a subregion in a simplex to each client, and
performs FL to learn a common solution simplex. This allows the client models
to possess their characteristics within the degrees of freedom in the solution
simplex, and at the same time achieves the goal of learning a global common
model. Our experiments show that SosicFL improves the performance and
accelerates the training process for global and personalized FL with minimal
computational overhead.

解决联邦学习中在高度异构的客户分布下取得良好性能的挑战，文章提出了用于解决这种矛盾的 Simplex 集群联邦学习方法（SosicFL）。通过将一个 Simplex 的子区域分配给每个客户端，并进行联邦学习来学习一个共同的解 Simplex，SosicFL 允许客户端模型在解 Simplex 的自由度内具有各自的特点，并同时实现学习一个全局共同模型的目标。我们的实验表明，SosicFL 提高了全局和个性化联邦学习的性能，并加速了训练过程，而计算开销很小。