CC-FedAvg: Computationally Customized Federated Averaging
- 31 July 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (3) , 4826-4841
Abstract
Federated learning (FL) is an emerging paradigm to train model with distributed data from numerous Internet of Things (IoT) devices. It inherently assumes a uniform capacity among participants. However, due to different conditions such as differing energy budgets or executing parallel unrelated tasks, participants have diverse computational resources in practice. Participants with insufficient computation budgets must plan for the use of restricted computational resources appropriately; otherwise, they would be unable to complete the entire training procedure, resulting in model performance decline. To address this issue, we propose a strategy for estimating local models without computationally intensive iterations. Based on it, we propose computationally customized federated averaging (CC-FedAvg), which allows participants to determine whether to perform traditional local training or model estimation in each round based on their current computational budgets. Both theoretical analysis and exhaustive experiments indicate that CC-FedAvg has the same convergence rate and comparable performance as FedAvg without resource constraints. Furthermore, CC-FedAvg can be viewed as a computation-efficient version of FedAvg that retains model performance while considerably lowering computation overhead.Keywords
All Related Versions
Funding Information
- National Key Research and Development Program of China (2021ZD0110900)
- National Natural Science Foundation of China (62106061, 61972114)
- Fundamental Research Funds for the Central Universities (FRFCU5710010521)
- Research and Application of Key Technologies for Intelligent Farming Decision Platform, An Open Competition Project of Heilongjiang Province (2021ZXJ05A03)
- Key Research and Development Program of Heilongjiang Province (2022ZX01A22)
- National Natural Science Foundation of Heilongjiang Province (YQ2019F007)
This publication has 10 references indexed in Scilit:
- FedCos: A Scene-Adaptive Enhancement for Federated LearningIEEE Internet of Things Journal, 2022
- Towards energy-aware federated learning on battery-powered clients2022
- Aperiodic Local SGD: Beyond Local SGD2022
- AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learning2021
- Advances and Open Problems in Federated LearningFoundations and Trends in Machine Learning, 2021
- Model-Contrastive Federated Learning2021
- Cost-Effective Federated Learning Design2021
- Faster Distributed Deep Net Training: Computation and Communication Decoupled Stochastic Gradient Descent2019
- CMFL: Mitigating Communication Overhead for Federated Learning2019
- Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge2019