A Correlation-Based Feature Weighting Filter for Naive Bayes
A Correlation-Based Feature Weighting Filter for Naive Bayes
复制标题
朴素贝叶斯基于相关性的特征加权滤波器
DOI：
10.1109/tkde.2018.2836440
复制
发表时间：
2019-02-01
影响因子：
8.9
通讯作者：
Wu, Jia
中科院分区：
文献类型：
--
作者：
Jiang, Liangxiao;Zhang, Lungan;Wu, Jia
由于其简单、高效和功效，朴素贝叶斯 (NB) 一直是数据挖掘和机器学习社区中十大算法之一。在减轻条件独立性假设的众多方法中，特征加权比那些预测性较低的特征更强调预测性高的特征。在本文中，我们认为对于 NB，高预测性特征应该与类别高度相关（最大相互相关性），但与其他特征不相关（最小相互冗余）。基于这个前提，我们提出了一种用于 NB 的基于相关性的特征加权（CFW）滤波器。在 CFW 中，特征的权重是特征类相关性（互相关性）和平均特征间相关性（平均互冗余性）之间差异的 sigmoid 变换。实验结果表明，带有 CFW 的 NB 显着优于 NB 和用于比较的所有其他现有最先进的特征加权滤波器。与用于改进 NB 的特征加权包装器相比，CFW 的主要优点是计算复杂度低（不涉及搜索）并且保持了最终模型的简单性。此外，我们将CFW应用于文本分类并取得了显着的改进。
Due to its simplicity, efficiency, and efficacy, naive Bayes (NB) has continued to be one of the top 10 algorithms in the data mining and machine learning community. Of numerous approaches to alleviating its conditional independence assumption, feature weighting has placed more emphasis on highly predictive features than those that are less predictive. In this paper, we argue that for NB highly predictive features should be highly correlated with the class (maximum mutual relevance), yet uncorrelated with other features (minimum mutual redundancy). Based on this premise, we propose a correlation-based feature weighting (CFW) filter for NB. In CFW, the weight for a feature is a sigmoid transformation of the difference between the feature-class correlation (mutual relevance) and the average feature-feature intercorrelation (average mutual redundancy). Experimental results show that NB with CFW significantly outperforms NB and all the other existing state-of-the-art feature weighting filters used to compare. Compared to feature weighting wrappers for improving NB, the main advantages of CFW are its low computational complexity (no search involved) and the fact that it maintains the simplicity of the final model. Besides, we apply CFW to text classification and have achieved remarkable improvements.