Compare Where It Matters: Using Layer-Wise Regularization To Improve Federated Learning on Heterogeneous Data
This addresses a key limitation in Federated Learning for distributed systems with heterogeneous data, offering improved performance and efficiency, though it is incremental as it builds on existing regularization approaches.
The paper tackles performance degradation in Federated Learning on heterogeneous data by identifying that only certain important layers require regularization, using Centered Kernel Alignment (CKA) to calculate layer similarity, and applying CKA-based regularization to these layers, resulting in FedCKA, which outperforms previous state-of-the-art methods on various deep learning tasks.
Federated Learning is a widely adopted method to train neural networks over distributed data. One main limitation is the performance degradation that occurs when data is heterogeneously distributed. While many works have attempted to address this problem, these methods under-perform because they are founded on a limited understanding of neural networks. In this work, we verify that only certain important layers in a neural network require regularization for effective training. We additionally verify that Centered Kernel Alignment (CKA) most accurately calculates similarity between layers of neural networks trained on different data. By applying CKA-based regularization to important layers during training, we significantly improve performance in heterogeneous settings. We present FedCKA: a simple framework that out-performs previous state-of-the-art methods on various deep learning tasks while also improving efficiency and scalability.