HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients

Abstract

Federated Learning (FL) is a method of training machine learning models on private data distributed over a large number of possibly heterogeneous clients such as mobile phones and IoT devices. In this work, we propose a new federated learning framework named HeteroFL to address heterogeneous clients equipped with very different computation and communication capabilities. Our solution can enable the training of heterogeneous local models with varying computation complexities and still produce a single global inference model. For the first time, our method challenges the underlying assumption of existing work that local models have to share the same architecture as the global model. We demonstrate several strategies to enhance FL training and conduct extensive empirical evaluations, including five computation complexity levels of three model architecture on three datasets. We show that adaptively distributing subnetworks according to clients' capabilities is both computation and communication efficient.

ICLR 2021

References in corpus (6)

• Towards Federated Learning at Scale: System Design
• FedMD: Heterogenous Federated Learning via Model Distillation
• Pointer Sentinel Mixture Models
• iDLG: Improved Deep Leakage from Gradients
• Threats to Federated Learning: A Survey
• LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets

Cited by in corpus (26)

• No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices
• Artificial Intelligence of Things: A Survey
• Hierarchical Personalized Federated Learning Over Massive Mobile Edge Computing Networks
• SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Training
• Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data
• AnycostFL: Efficient On-Demand Federated Learning over Heterogeneous Edge Devices
• FLrce: Resource-Efficient Federated Learning with Early-Stopping Strategy
• AdaptiveFL: Adaptive Heterogeneous Federated Learning for Resource-Constrained AIoT Systems
• Federated Reconstruction: Partially Local Federated Learning
• Personalized Federated Learning through Local Memorization
• FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning
• Federated Learning for Energy Constrained IoT devices: A systematic mapping study
• Federated Stain Normalization for Computational Pathology
• What Do We Mean by Generalization in Federated Learning?
• Personalised Federated Learning On Heterogeneous Feature Spaces
• GAL: Gradient Assisted Learning for Decentralized Multi-Organization Collaborations
• A Framework for Verifiable and Auditable Federated Anomaly Detection
• FedPrune: Towards Inclusive Federated Learning
• AdaptCL: Efficient Collaborative Learning with Dynamic and Adaptive Pruning
• Assisted Learning for Organizations with Limited Imbalanced Data
• An Operator Splitting View of Federated Learning
• Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems
• Federated Learning via Plurality Vote
• Communication Efficient Federated Learning with Adaptive Quantization
• HADFL: Heterogeneity-aware Decentralized Federated Learning Framework
• MyMigrationBot: A Cloud-based Facebook Social Chatbot for Migrant Populations