Federated Learning with Matched Averaging

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 not only outperforms popular state-of-the-art federated learning algorithms on deep CNN and LSTM architectures trained on real world datasets, but also reduces the overall communication burden.

Accepted by ICLR 2020

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• On the Convergence of Adam and Beyond
• Towards Federated Learning at Scale: System Design
• No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World
• Bayesian Nonparametric Federated Learning of Neural Networks

Cited by in corpus (24)

• A Field Guide to Federated Optimization
• A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and Comparison
• FedMix: Approximation of Mixup under Mean Augmented Federated Learning
• No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data
• Auto-FedAvg: Learnable Federated Averaging for Multi-Institutional Medical Image Segmentation
• Fairness and Accuracy in Federated Learning
• A distillation-based approach integrating continual learning and federated learning for pervasive services
• A Systematic Literature Review on Federated Learning: From A Model Quality Perspective
• Model-Contrastive Federated Learning
• Adversarial training in communication constrained federated learning
• FedCCEA : A Practical Approach of Client Contribution Evaluation for Federated Learning
• Personalized Federated Learning with Gaussian Processes
• Towards Unsupervised Domain Adaptation for Deep Face Recognition under Privacy Constraints via Federated Learning
• Hybrid Federated Learning: Algorithms and Implementation
• Federated Learning on Non-IID Data: A Survey
• Decentralised Person Re-Identification with Selective Knowledge Aggregation
• Federated CycleGAN for Privacy-Preserving Image-to-Image Translation
• On Large-Cohort Training for Federated Learning
• Federated Learning for Open Banking
• Critical Learning Periods in Federated Learning
• Personalized Retrogress-Resilient Framework for Real-World Medical Federated Learning
• Dynamic Attention-based Communication-Efficient Federated Learning
• Exact Support Recovery in Federated Regression with One-shot Communication
• FedNS: Improving Federated Learning for collaborative image classification on mobile clients