一种基于学习自动机的推荐算法改进  

Learning automata-based improvement for recommendation algorithm

作　　者：荆羽纯 葛昊[1] 江文[1] 王伊凡[1] 

机构地区：[1]上海交通大学电子信息与电气工程学院,上海200240

出　　处：《计算机应用研究》2016年第1期32-34,41,共4页Application Research of Computers

基　　金：国家自然科学基金资助项目(61271316);国家"973"计划资助项目(2013CB329603;2013CB329605);上海市信息安全综合管理技术研究重点实验室基金;信息内容分析技术国家工程实验室基金资助项目

摘　　要：针对原有的基于隐语义模型(LFM)的推荐算法中,当训练样本数减少时,训练误差和测试误差都明显增大的问题进行改进研究,提出了一种全新的基于学习自动机的矩阵训练算法。该算法充分利用连续型学习自动机在随机和高噪声环境中优化参数的卓越性能,代替原有的梯度下降算法进行大型稀疏矩阵的奇异值分解计算,使得重构矩阵与原矩阵之间的误差进一步降低,提高了后续预测算法的精确度。为了检验新算法的寻优性能,在大量真实用户对电影的评分数据集上进行了新旧两种算法的对比实验,实验结果表明改进后的基于学习自动机的推荐算法在样本数较少和更随机的测试环境中,相比原算法可以实现更精确的预测,有效地弥补了原算法的不足。To solve the problem of an obvious rise in error as the decrease of the number of training samples in the recommen- dation algorithm based on latent factor model （ LFM）, this paper proposed a new training algorithm based on continuous ac- tions learning automata （CALA）. The new algorithm took use of the superior property of continuous learning automata on opti- mizing parameters in a more random environment. Then the new algorithm insteaded of the original gradient descent algorithm, to perform the singular value decomposition （SVD） , which could achieve a smaller error between the reconstructed matrix and the original matrix, and then it reduced the forecast error. To analysis the optimization performance of the new algorithm, this paper made a test based on a real movie rating data set, and compared the forecast result with that of the original algorithm. The results indicate that the CALA-based training algorithm can behave better than the original algorithm in a more random en- vironment and achieve a more accurate forecast effect.

关 键 词：学习自动机 奇异值分解 推荐算法 隐语义模型 梯度下降算法 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TP301.6[自动化与计算机技术—控制科学与工程]