Compare Where It Matters: Using Layer-Wise Regularization To Improve Federated Learning on Heterogeneous Data
arXiv:2112.00407 · doi:10.3390/app12199943
Abstract
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.
arXiv comment8 pages, 5 figures, 4 tables
References in corpus (9)
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- A Simple Framework for Contrastive Learning of Visual Representations
- A Survey on Distributed Machine Learning
- SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
- Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
- Ensemble Distillation for Robust Model Fusion in Federated Learning
- Distributed Federated Learning for Ultra-Reliable Low-Latency Vehicular Communications
- Similarity of Neural Network Representations Revisited
- Are All Layers Created Equal?