混合模型下的雅可比矩阵退火算法优化

1)河北师范大学计算机与网络空间安全学院, 人工智能研究中心, 河北石家庄 050024; 2)伊利诺伊大学香槟分校信息科学学院,厄巴纳-香槟市 61801,美国; 3)河北工程技术学院人工智能与大数据学院,河北石家庄 050091; 4)河北地质大学信息工程学院,河北石家庄 050031

人工智能理论; 复杂网络; 混合模型; 退火算法; 收敛速度; 雅可比矩阵; 半监督学习

Optimization of Jacobian matrix annealing algorithm based on hybrid model
WANG Jinghong1, 2, FENG Chan3, and CHAI Bianfang4

1)Artificial Intelligence Research Center, College of Computer and cyber Sceurity, Hebei Normal University, Shijiazhuang 050024, Hebei Province, P.R.China2)School of Information Science, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA3)College of Artificial Intelligence Big Data, Hebei Institute of Engineering Technology, Shijiazhuang 050091, Hebei Province, P.R.China4)College of Information Engineering, Hebei GEO University, Shijiazhuang 050031, Hebei Province, P.R.China

artificial intelligence theory; complex network; hybrid model; annealing algorithm; convergence rate; Jacobian matrix; semi-supervised learning

DOI: 10.3724/SP.J.1249.2021.02188

备注

退火算法可有效发现网络结构的聚类分布情况,但在不同的网络中算法处理结果的准确性有待提高.为更精确地识别混合模型网络结构中的数据分布,解决混合模型易陷入局部最大值和收敛等问题,提出混合模型下雅可比矩阵退火算法.首先利用逆温度参数β对模型进行初始化,然后迭代执行计算期望步骤和最大化步骤2个任务; 采用雅可比矩阵计算模型的后验概率,直至算法达到设定的准确性或收敛.将建立的雅可比矩阵退火算法与半监督高斯混合模型下的逆模拟退火聚类算法在真实网络上进行对比分析,实验结果表明,基于雅可比矩阵的算法在混合网络模型中的准确性更优.该算法不仅能防止陷入局部最优,而且能提高分析网络聚类分布的准确性.

The annealing algorithm can effectively find the clustering distribution of network structure, but the algorithm accuracy of handling different networks needs to be further improved. In order to identify the data distribution in network structure of mixed model more accurately and solve the problems of local maximum value and convergence of mixed model, the Jacobian matrix annealing algorithm is studied. First, the model is initialized by using the inverse temperature parameter, and then the two tasks of expectation step and maximization step are performed iteratively. The posterior probability of model is calculated based on the Jacobian matrix until the algorithm reaches the set accuracy or meets the convergence condition. The Jacobian matrix annealing algorithm is compared with the inverse simulated annealing clustering algorithm under semi-supervised Gaussian mixture model on the real network, and the experimental results show that the accuracy of Jacobian matrix algorithm in the hybrid network model is better. The proposed algorithm can not only prevent the network from falling into the local optimum, but also improve the accuracy of analyzing network clustering distribution.

·