摘要
在多标签学习中,利用标签相关性提升预测性能是研究重点.基于矩阵分解的方法通过构建潜在标签,获得从数据到标签空间更本质的映射.然而,实数矩阵分解缺乏语义解释,且常用的线性映射拟合能力有限.因此,本文提出了一种基于布尔矩阵分解和神经网络的多标签学习方法MLBF.具体而言,布尔矩阵维持了标签关于有/无的语义特征,利用所提出的启发式分解算法效率高且效果好;神经网络提供非线性的拟合能力,且有效利用并行计算资源以应对大数据集.本研究在13个基准数据集上进行了实验,采用了8种流行的算法进行比较,并通过5个常用指标对它们进行了评估.实验结果表明,MLBF在这些指标的平均排名分别为1.92,2.5,2.38,2.23,2.46.
In multi-label learning,utilizing label correlation to improve prediction performance is a research focus.Mining label correlation is an important content.The method based on matrix decomposition obtains a more essential mapping from data to label space by constructing potential labels.However,real number matrix decomposition lacks semantic interpretation and the commonly used linear mapping fitting ability is limited.Therefore,this article proposes a multi-label learning method MLBF based on Boolean matrix factorization and neural networks.Specifically,the Boolean matrix maintains the semantic features of labels regarding presence/absence,and the proposed heuristic decomposition algorithm is efficient and effective;neural networks provide nonlinear fitting capabilities and effectively utilize parallel computing resources to cope with large datasets.This study conducted experiments on 13 benchmark datasets,compared 8 popular algorithms,and evaluated them using 5 commonly used indicators.The experimental results show that the mean ranking of MLBF in these indicators is 1.92,2.5,2.38,2.23,and 2.46,respectively.
作者
霍一帆
王轩
董小铭
于洪
闵帆
HUO Yifan;WANG Xuan;DONG Xiaoming;YU Hong;MIN Fan(School of Computer Science and Software Engineering,Southwest Petroleum University,Chengdu 610500,China;Network and Information Center,Southwest Petroleum University,Chengdu 610500,China;School of Sciences,Southwest Petroleum University,Chengdu 610500,China;Chongqing Municipal Key Laboratory of Computing Intelligence,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;Lab of Machine Learning,Southwest Petroleum University,Chengdu 610500,China)
出处
《昆明理工大学学报（自然科学版）》
北大核心
2024年第2期49-61,共13页
Journal of Kunming University of Science and Technology(Natural Science)
基金
国家自然科学基金重点项目(62136002)
国家社科基金项目(22FZXB092)
南充市科技局重点项目(23XNSYSX0062)。
关键词
布尔矩阵分解
多标签学习
神经网络
Boolean matrix factorization
multi-label learning
neural networks
