PSO + FL = PAASO: particle swarm optimization + federated learning = privacy-aware agent swarm optimization
نویسندگان
چکیده
Abstract In this paper, we present an unified framework that encompasses both particle swarm optimization (PSO) and federated learning (FL). This shows can understand PSO FL in terms of a function to be optimized by set agents but which have different privacy requirements. is the most relaxed case, considers slightly stronger constraints. Even requirements considered will lead still privacy-preserving solutions. Differentially private solutions as well local differential privacy/reidentification for opinions are additional models considered. discuss privacy-related alternatives. We experiments show how degrade results system. To end, consider problems compatible with FL.
منابع مشابه
Particle Swarm Optimization (PSO) based Tool Position Error Optimization
High-precision tool positioning is one of the fundamental requirements for the industry now-a-days. Earlier, tool positioning and its verification were done using sensors etc. In this paper, an algorithm has been proposed to increase the tool positioning accuracy by analyzing the information obtained using CCD camera. The images of lathe tool are used for carrying out the experiments. Firstly, ...
متن کاملCutting Parameters Optimization by Using Particle Swarm Optimization (PSO)
Cutting parameters play an essential role in the economics of machining. In this paper, particle swarm optimization (PSO), a novel optimization algorithm for cutting parameters optimization (CPO), was discussed comprehensively. First, the fundamental principle of PSO was introduced; then, the algorithm for PSO application in cutting parameters optimization was developed; thirdly, cutting experi...
متن کاملFeedback learning particle swarm optimization
In this paper, a feedback learning particle swarm optimization algorithm with quadratic inertia weight (FLPSOQIW) is developed to solve optimization problems. The proposed FLPSO-QIW consists of four steps. Firstly, the inertia weight is calculated by a designed quadratic function instead of conventional linearly decreasing function. Secondly, acceleration coefficients are determined not only by...
متن کاملLearning in Particle Swarm Optimization
This paper presents particle swarm optimization based on learning from winner particle. (PSO-WS). Instead of considering gbest and pbest particle for position update, each particle considers its distance from immediate winner to update its position. Only winner particle follow general velocity and position update equation. If this strategy performs well for the particle, then that particle upda...
متن کاملMulti-Objective Design Optimization of a Linear Brushless Permanent Magnet Motor Using Particle Swarm Optimization (PSO)
In this paper a brushless permanent magnet motor is designed considering minimum thrust ripple and maximum thrust density (the ratio of the thrust to permanent magnet volumes). Particle Swarm Optimization (PSO) is used as optimization method. Finite element analysis (FEA) is carried out base on the optimized and conventional geometric dimensions of the motor. The results of the FEA deal to ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: International Journal of Information Security
سال: 2022
ISSN: ['1615-5262', '1615-5270']
DOI: https://doi.org/10.1007/s10207-022-00614-6