Over-the-Air Decentralized Federated Learning

In this paper, we consider decentralized federated learning (FL) over wireless networks, where over-the-air computation (AirComp) is adopted to facilitate the local model consensus in a device-to-device (D2D) communication manner. However, the AirComp-based consensus phase brings the additive noise in each algorithm iterate and the consensus needs to be robust to wireless network topology changes, which introduce a coupled and novel challenge of establishing the convergence for wireless decentralized FL algorithm. To facilitate consensus phase, we propose an AirComp-based DSGD with gradient tracking and variance reduction (DSGT-VR) algorithm, where both precoding and decoding strategies are developed for D2D communication. Furthermore, we prove that the proposed algorithm converges linearly and establish the optimality gap for strongly convex and smooth loss functions, taking into account the channel fading and noise. The theoretical result shows that the additional error bound in the optimality gap depends on the number of devices. Extensive simulations verify the theoretical results and show that the proposed algorithm outperforms other benchmark decentralized FL algorithms over wireless networks.

[1]  Jie Xu,et al.  D2D-Enabled Data Sharing for Distributed Machine Learning at Wireless Network Edge , 2020, IEEE Wireless Communications Letters.

[2]  Deniz Gündüz,et al.  Decentralized SGD with Over-the-Air Computation , 2020, GLOBECOM 2020 - 2020 IEEE Global Communications Conference.

[3]  Richard Nock,et al.  Advances and Open Problems in Federated Learning , 2021, Found. Trends Mach. Learn..

[4]  Liangzhong Ruan,et al.  Interference Alignment for Partially Connected MIMO Cellular Networks , 2012, IEEE Transactions on Signal Processing.

[5]  Angelia Nedic,et al.  Distributed stochastic gradient tracking methods , 2018, Mathematical Programming.

[6]  Yong Zhou,et al.  Federated Machine Learning for Intelligent IoT via Reconfigurable Intelligent Surface , 2020, IEEE Network.

[7]  Stephen P. Boyd,et al.  Fast linear iterations for distributed averaging , 2003, 42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475).

[8]  Zhibin Wang,et al.  Wireless-Powered Over-the-Air Computation in Intelligent Reflecting Surface-Aided IoT Networks , 2021, IEEE Internet of Things Journal.

[9]  Syed Ali Jafar,et al.  Topological Interference Management Through Index Coding , 2013, IEEE Transactions on Information Theory.

[10]  Yuanming Shi,et al.  Delay Analysis of Wireless Federated Learning Based on Saddle Point Approximation and Large Deviation Theory , 2021, IEEE Journal on Selected Areas in Communications.

[11]  Zhi Ding,et al.  Blind Over-the-Air Computation and Data Fusion via Provable Wirtinger Flow , 2018, IEEE Transactions on Signal Processing.

[12]  U. Khan,et al.  Variance-Reduced Decentralized Stochastic Optimization With Accelerated Convergence , 2019, IEEE Transactions on Signal Processing.

[13]  Zhi Ding,et al.  Federated Learning via Over-the-Air Computation , 2018, IEEE Transactions on Wireless Communications.

[14]  Ying-Chang Liang,et al.  Federated Learning in Mobile Edge Networks: A Comprehensive Survey , 2020, IEEE Communications Surveys & Tutorials.

[15]  Kobi Cohen,et al.  On Analog Gradient Descent Learning Over Multiple Access Fading Channels , 2019, IEEE Transactions on Signal Processing.

[16]  Deniz Gündüz,et al.  Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Air , 2019, 2019 IEEE International Symposium on Information Theory (ISIT).

[17]  Zhibin Wang,et al.  Federated Learning via Intelligent Reflecting Surface , 2020, IEEE Transactions on Wireless Communications.

[18]  Wei Chen,et al.  The Roadmap to 6G: AI Empowered Wireless Networks , 2019, IEEE Communications Magazine.

[19]  Halim Yanikomeroglu,et al.  Device-to-device communication in 5G cellular networks: challenges, solutions, and future directions , 2014, IEEE Communications Magazine.

[20]  B. Reed.  Graph Colouring and the Probabilistic Method , 2001 .

[21]  Solmaz Niknam,et al.  Federated Learning for Wireless Communications: Motivation, Opportunities, and Challenges , 2019, IEEE Communications Magazine.

[22]  Wei Zhang,et al.  Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent , 2017, NIPS.

[23]  M. Bennis,et al.  Joint Parameter-and-Bandwidth Allocation for Improving the Efficiency of Partitioned Edge Learning , 2020, IEEE Transactions on Wireless Communications.

[24]  H. Vincent Poor,et al.  Convergence Time Optimization for Federated Learning Over Wireless Networks , 2020, IEEE Transactions on Wireless Communications.

[25]  Martin Jaggi,et al.  A Unified Theory of Decentralized SGD with Changing Topology and Local Updates , 2020, ICML.

[26]  Soummya Kar,et al.  Decentralized Stochastic Optimization and Machine Learning: A Unified Variance-Reduction Framework for Robust Performance and Fast Convergence , 2020, IEEE Signal Processing Magazine.

[27]  Yan Zhang,et al.  Blockchain and Federated Learning for Privacy-Preserved Data Sharing in Industrial IoT , 2020, IEEE Transactions on Industrial Informatics.

[28]  Jun Zhang,et al.  Communication-Efficient Edge AI: Algorithms and Systems , 2020, IEEE Communications Surveys & Tutorials.

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

[30]  Mehdi Bennis,et al.  Opportunities of Federated Learning in Connected, Cooperative, and Automated Industrial Systems , 2021, IEEE Communications Magazine.

[31]  Mohsen Guizani,et al.  A Survey on Federated Learning: The Journey From Centralized to Distributed On-Site Learning and Beyond , 2021, IEEE Internet of Things Journal.

[32]  Shuguang Cui,et al.  Federated Learning for 6G: Applications, Challenges, and Opportunities , 2021, Engineering.

[33]  Kaibin Huang,et al.  Over-the-Air Computing for 6G - Turning Air into a Computer , 2020, ArXiv.

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

[35]  Mehdi Bennis,et al.  A Joint Decentralized Federated Learning and Communications Framework for Industrial Networks , 2020, 2020 IEEE 25th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD).

[36]  Na Li,et al.  Harnessing smoothness to accelerate distributed optimization , 2016, 2016 IEEE 55th Conference on Decision and Control (CDC).

[37]  Osvaldo Simeone,et al.  Decentralized Federated Learning via SGD over Wireless D2D Networks , 2020, 2020 IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[38]  Praveen Kumar Reddy Maddikunta,et al.  Fusion of Federated Learning and Industrial Internet of Things: A Survey , 2021, Comput. Networks.