Class-specific attribute value weighting for Naive Bayes
Class-specific attribute value weighting for Naive Bayes
复制标题
朴素贝叶斯的类特定属性值加权
DOI:
10.1016/j.ins.2019.08.071
复制
发表时间:
2020
影响因子:
8.1
通讯作者:
Yu Liangjun
中科院分区:
文献类型:
--
作者:
Zhang Huan;Jiang Liangxiao;Yu Liangjun
Naive Bayes (NB) is one of the top 10 data mining algorithms. However, its assumption of conditional independence rarely holds true in real-world applications. To alleviate this assumption, numerous attribute weighting approaches have been proposed. However, few of these simultaneously pay attention to the horizontal granularity of attribute values and vertical granularity of class labels. In this study, we propose a new paradigm for fine-grained attribute weighting, named class-specific attribute value weighting. For each class, this approach discriminatively assigns a specific weight to each attribute value. We refer to the resulting improved model as class-specific attribute value weighted NB (CAVWNB). In CAVWNB, the class-specific attribute value weight matrix is learned by either maximizing the conditional log-likelihood (CLL) or minimizing the mean squared error (MSE). Thus, two versions are proposed, which we denote as CAVWNBCLLand CAVWNBMSE, respectively. Extensive experimental results on a large number of datasets show that both CAVWNBCLLand CAVWNBMSEsignificantly outperform NB and all the other existing state-of-the-art attribute weighting approaches used for comparison.
登录
查看更多内容
DOI:
10.1007/s13042-013-0152-x
发表时间:
2014-04-01
影响因子:
5.6
作者:
Jiang, Liangxiao;Cai, Zhihua;Zhang, Harry
通讯作者:
Zhang, Harry
影响因子:
5.1
作者:
Li, Chaoqun;Jiang, Liangxiao;Li, Hongwei
通讯作者:
Li, Hongwei
DOI:
--
发表时间:
2014
期刊:
Journal of management science
影响因子:
--
作者:
อนิรุธ สืบสิงห์
通讯作者:
อนิรุธ สืบสิงห์
DOI:
10.1109/tsmc.2018.2828018
发表时间:
2020-04
期刊:
IEEE Transactions on Systems, Man, and Cybernetics: Systems
影响因子:
--
作者:
Wenyin Gong;Yong Wang;Z. Cai;Ling Wang
通讯作者:
Wenyin Gong;Yong Wang;Z. Cai;Ling Wang
影响因子:
5.1
作者:
Jiang, Liangxiao;Li, Chaoqun;Wang, Shasha
通讯作者:
Wang, Shasha