多层克隆选择的排序学习方法研究  

A Learning to Rank Method Based on Multi-layer Clonal Selection

作　　者：武宇婷 张子旸 田玉玲 张弘弦 WU Yuting;ZHANG Ziyang;TIAN Yuling;ZHANG Hongxian(College of Information and Computer,Taiyuan University of Technology,Taiyuan 030024,China;School of Electronic Information and Electrical Engineering,Shanghai Jiaotong University,Shanghai 200030,China)

机构地区：[1]太原理工大学信息与计算机学院,太原030024 [2]上海交通大学电子信息与电气工程学院,上海200030

出　　处：《太原理工大学学报》2018年第5期751-758,共8页Journal of Taiyuan University of Technology

基　　金：国家自然科学基金资助项目(61472271);山西省基础研究资助项目(2015021106)

摘　　要：提出一种基于多层克隆选择的排序学习方法,将克隆选择理论应用于学习排序函数,对传统克隆选择进行改进,使用一种按层变异的方法和一种多层的克隆选择架构逐步进化抗体库,最终得到最优的排序函数。提出的方法在LETOR基准数据集进行评价,结果表明了算法在多数情况下优于基线算法。A learning to rank method based on multi-layer clonal selection is presented.The clonal selection theory is applied to learn ranking functions and an improvement is applied to the traditional clonal selection algorithm.A layered mutation method and a multi-layer clonal selection architecture are used to evolve antibody repertoire and get the optimal ranking function.Proposed method is evaluated on the LETOR data collection,and results show that the proposed algorithm is more effective than baseline algorithms in most cases.

关 键 词：克隆选择 排序学习 排序函数 

分 类 号：TP31[自动化与计算机技术—计算机软件与理论]