Heterogeneous fairness algorithm based on federated learning in intelligent transportation system

With the development of the Intelligent Transportation System, various distributed sensors (including GPS, radar, infrared sensors) process massive data and make decisions for emergencies. Federated learning is a new distributed machine learning paradigm, in which system heterogeneity is the difficulty of fairness design. This paper designs a system heterogeneous fair federated learning algorithm (SHFF). SHFF introduces the equipment influence factor I into the optimization target and dynamically adjusts the equipment proportion with other performance. By changing the global fairness parameter θ, the algorithm can control fairness according to the actual needs. Experimental results show that, compared with the popular q-FedAvg algorithm, the SHFF algorithm proposed in this paper improves the average accuracy of the Worst 10% by 26% and reduces the variance by 61%.

[1]  Thorsten Joachims,et al.  Making large scale SVM learning practical , 1998 .

[2]  Fabio Dovis,et al.  Recent Advancement on the Use of Global Navigation Satellite System-Based Positioning for Intelligent Transport Systems [Guest Editorial] , 2020, IEEE Intell. Transp. Syst. Mag..

[3]  Barbara Caputo,et al.  Recognizing human actions: a local SVM approach , 2004, ICPR 2004.

[4]  Alexander Nebylov,et al.  Integrated Navigation and Distributed Control Intelligent Transport System , 2020, 2020 27th Saint Petersburg International Conference on Integrated Navigation Systems (ICINS).

[5]  Local Lipschitz-constant Functions and Maximal Subdifferentials , 2003 .

[6]  Elijah Blessing Rajsingh,et al.  Classification of Road Accidents Using SVM and KNN , 2020 .

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

[8]  B. Jaumard,et al.  On using estimates of Lipschitz constants in global optimization , 1990 .

[9]  Yu Hen Hu,et al.  Vehicle classification in distributed sensor networks , 2004, J. Parallel Distributed Comput..

[10]  Ming Liu,et al.  Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems With Heterogeneous Sensor Data , 2019, IEEE Robotics and Automation Letters.

[11]  Nageen Himayat,et al.  Resource Management and Fairness for Federated Learning over Wireless Edge Networks , 2020, 2020 IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[12]  Oleksandr Romanko,et al.  Normalization and Other Topics in Multi­Objective Optimization , 2006 .

[13]  B. P. Zhang,et al.  Estimation of the Lipschitz constant of a function , 1996, J. Glob. Optim..

[14]  Byung Tae Chun,et al.  Design of real time vehicle identification system , 1994, Proceedings of IEEE International Conference on Systems, Man and Cybernetics.

[15]  Kai Da,et al.  A Computationally Efficient Approach for Distributed Sensor Localization and Multitarget Tracking , 2020, IEEE Communications Letters.