Federated Learning with Matched Averaging

Anonymous

Sep 25, 2019 ICLR 2020 Conference Blind Submission readers: everyone Show Bibtex
  • TL;DR: Communication efficient federated learning with layer-wise matching
  • Abstract: Federated learning allows edge devices to collaboratively learn a shared model while keeping the training data on device, decoupling the ability to do model training from the need to store the data in the cloud. We propose Federated matched averaging (FedMA) algorithm designed for federated learning of modern neural network architectures e.g. convolutional neural networks (CNNs) and LSTMs. FedMA constructs the shared global model in a layer-wise manner by matching and averaging hidden elements (i.e. channels for convolution layers; hidden states for LSTM; neurons for fully connected layers) with similar feature extraction signatures. Our experiments indicate that FedMA outperforms popular state-of-the-art federated learning algorithms on deep CNN and LSTM architectures trained on real world datasets, while improving the communication efficiency.
  • Keywords: federated learning
0 Replies

Loading