Prophet: Proactive Candidate-Selection for Federated Learning by Predicting the Qualities of Training and Reporting Phases
This addresses latency issues for FL systems in dynamic environments like 5G networks, representing an incremental improvement over prior reactive methods.
The paper tackles the problem of high training latency in Federated Learning (FL) due to poor candidate-selection by proposing a proactive approach that predicts device qualities using LSTM and selects candidates via Deep Reinforcement Learning, achieving improved performance over existing reactive algorithms in real-world trace-driven experiments.
Although the challenge of the device connection is much relieved in 5G networks, the training latency is still an obstacle preventing Federated Learning (FL) from being largely adopted. One of the most fundamental problems that lead to large latency is the bad candidate-selection for FL. In the dynamic environment, the mobile devices selected by the existing reactive candidate-selection algorithms very possibly fail to complete the training and reporting phases of FL, because the FL parameter server only knows the currently-observed resources of all candidates. To this end, we study the proactive candidate-selection for FL in this paper. We first let each candidate device predict the qualities of both its training and reporting phases locally using LSTM. Then, the proposed candidateselection algorithm is implemented by the Deep Reinforcement Learning (DRL) framework. Finally, the real-world trace-driven experiments prove that the proposed approach outperforms the existing reactive algorithms