4.7 Article

Neighborhood representative for improving outlier detectors

期刊

INFORMATION SCIENCES
卷 625, 期 -, 页码 192-205

出版社

ELSEVIER SCIENCE INC
DOI: 10.1016/j.ins.2022.12.041

关键词

Outlier detection; Preprocessing; Neighborhood representative; K nearest neighbors

向作者/读者索取更多资源

Traditional outlier detectors have neglected the group-level factor in calculating outlier scores for objects in data, resulting in the inability to capture collective outliers. To address this issue, a framework called neighborhood representative (NR) is proposed, enabling existing outlier detectors to efficiently detect outliers, including collective outliers, while maintaining computational integrity. By selecting representative objects, scoring them, and applying the score to collective objects, NR achieves this without altering existing detectors. NR is compatible with existing detectors and improves performance on eleven real-world datasets by an average of 8% (0.72 to 0.78 AUC) relative to twelve state-of-the-art outlier detectors. The implementation of NR can be found at www.OutlierNet.com for reproducibility. (c) 2022 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
Over the decades, traditional outlier detectors have ignored the group-level factor when calculating outlier scores for objects in data by evaluating only the object-level factor, fail-ing to capture the collective outliers. To mitigate this issue, we present a framework called neighborhood representative (NR), which empowers all the existing outlier detectors to effi-ciently detect outliers, including collective outliers, while maintaining their computational integrity. It achieves this by selecting representative objects, scoring these objects, then applies the score of the representative objects to its collective objects. Without altering existing detectors, NR is compatible with existing detectors, while improving performance on eleven real world datasets with +8 % (0.72 to 0.78 AUC) on average relative to twelve state-of-the-art outlier detectors. The implementation of NR can be found via www. OutlierNet.com for reproducibility.(c) 2022 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据