SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Training
arXiv:2106.01432
Abstract
Federated Learning allows the training of machine learning models by using the computation and private data resources of many distributed clients. Most existing results on Federated Learning (FL) assume the clients have ground-truth labels. However, in many practical scenarios, clients may be unable to label task-specific data due to a lack of expertise or resource. We propose SemiFL to address the problem of combining communication-efficient FL such as FedAvg with Semi-Supervised Learning (SSL). In SemiFL, clients have completely unlabeled data and can train multiple local epochs to reduce communication costs, while the server has a small amount of labeled data. We provide a theoretical understanding of the success of data augmentation-based SSL methods to illustrate the bottleneck of a vanilla combination of communication-efficient FL with SSL. To address this issue, we propose alternate training to `fine-tune global model with labeled data' and `generate pseudo-labels with the global model.' We conduct extensive experiments and demonstrate that our approach significantly improves the performance of a labeled server with unlabeled clients training with multiple local epochs. Moreover, our method outperforms many existing SSFL baselines and performs competitively with the state-of-the-art FL and SSL results.
References in corpus (17)
- Temporal Ensembling for Semi-Supervised Learning
- Towards Federated Learning at Scale: System Design
- FedMD: Heterogenous Federated Learning via Model Distillation
- FedML: A Research Library and Benchmark for Federated Machine Learning
- Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Data
- FedBN: Federated Learning on Non-IID Features via Local Batch Normalization
- HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients
- ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring
- Federated Learning Based on Dynamic Regularization
- Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data
- LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets
- SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum
- FedMix: Approximation of Mixup under Mean Augmented Federated Learning
- Semi-supervised Federated Learning for Activity Recognition
- Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of Models
- Communication-Efficient Federated Distillation
- Exploiting Unlabeled Data in Smart Cities using Federated Learning