Prophet: Proactive Candidate-Selection for Federated Learning by Predicting the Qualities of Training and Reporting Phases

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

[1]  Blaise Agüera y Arcas,et al.  Communication-Efficient Learning of Deep Networks from Decentralized Data , 2016, AISTATS.

[2]  Alex Graves,et al.  Playing Atari with Deep Reinforcement Learning , 2013, ArXiv.

[3]  David Silver,et al.  Deep Reinforcement Learning with Double Q-Learning , 2015, AAAI.

[4]  Walid Saad,et al.  A Joint Learning and Communications Framework for Federated Learning Over Wireless Networks , 2021, IEEE Transactions on Wireless Communications.

[5]  Chao Zhang,et al.  DeepMove: Predicting Human Mobility with Attentional Recurrent Networks , 2018, WWW.

[6]  Albert-László Barabási,et al.  Understanding individual human mobility patterns , 2008, Nature.

[7]  Hubert Eichner,et al.  Towards Federated Learning at Scale: System Design , 2019, SysML.

[8]  Ryosuke Shibasaki,et al.  DeepUrbanEvent: A System for Predicting Citywide Crowd Dynamics at Big Events , 2019, KDD.

[9]  Weigang Wu,et al.  Predictive Online Server Provisioning for Cost-Efficient IoT Data Streaming Across Collaborative Edges , 2019, MobiHoc.

[10]  Hongzhi Shi,et al.  State-Sharing Sparse Hidden Markov Models for Personalized Sequences , 2019, KDD.

[11]  Hubert Eichner,et al.  Federated Learning for Mobile Keyboard Prediction , 2018, ArXiv.

[12]  Jing Li,et al.  Predicting Activity and Location with Multi-task Context Aware Recurrent Neural Network , 2018, IJCAI.

[13]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[14]  Takayuki Nishio,et al.  Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge , 2018, ICC 2019 - 2019 IEEE International Conference on Communications (ICC).

[15]  Sarvar Patel,et al.  Practical Secure Aggregation for Privacy-Preserving Machine Learning , 2017, IACR Cryptol. ePrint Arch..

[16]  Yuanyuan Qiao,et al.  Big Data Driven Hidden Markov Model Based Individual Mobility Prediction at Points of Interest , 2017, IEEE Transactions on Vehicular Technology.

[17]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .