Robust Federated Learning Through Representation Matching and Adaptive Hyper-parameters

Abstract

Federated learning is a distributed, privacy-aware learning scenario which trains a single model on data belonging to several clients. Each client trains a local model on its data and the local models are then aggregated by a central party. Current federated learning methods struggle in cases with heterogeneous client-side data distributions which can quickly lead to divergent local models and a collapse in performance. Careful hyper-parameter tuning is particularly important in these cases but traditional automated hyper-parameter tuning methods would require several training trials which is often impractical in a federated learning setting. We describe a two-pronged solution to the issues of robustness and hyper-parameter tuning in federated learning settings. We propose a novel representation matching scheme that reduces the divergence of local models by ensuring the feature representations in the global (aggregate) model can be derived from the locally learned representations. We also propose an online hyper-parameter tuning scheme which uses an online version of the REINFORCE algorithm to find a hyper-parameter distribution that maximizes the expected improvements in training loss. We show on several benchmarks that our two-part scheme of local representation matching and global adaptive hyper-parameters significantly improves performance and training robustness.

References in corpus (13)

• Practical Bayesian Optimization of Machine Learning Algorithms
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Federated Learning: Strategies for Improving Communication Efficiency
• Federated Learning with Non-IID Data
• Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
• Semi-Supervised Learning with Ladder Networks
• Federated Optimization in Heterogeneous Networks
• Wasserstein Distance Guided Representation Learning for Domain Adaptation
• Stacked What-Where Auto-encoders
• Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets
• Stochastic Hyperparameter Optimization through Hypernetworks
• Hyp-RL : Hyperparameter Optimization by Reinforcement Learning
• Reinforcement Learning for Learning Rate Control

Cited by in corpus (4)

• CDKT-FL: Cross-Device Knowledge Transfer using Proxy Dataset in Federated Learning
• Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing
• Adversarial Robustness through Bias Variance Decomposition: A New Perspective for Federated Learning
• Fed2: Feature-Aligned Federated Learning