arXiv cs.AI· Muhammad Rajabinasab, Michael E. Houle, Oussama Chelly, Arthur Zimek·· 14 小时前AI 评分22
比随机还差：无监督特征选择为何需要随机基线（扩展版）
Worse than Random: The Importance of a Baseline for Unsupervised Feature Selection -- Extended Version
AI 导读
一项评估研究以随机特征选择作为基线，发现无监督特征选择领域许多 SOTA 方法在性能与效率上均被随机选择超越。作者据此强调，新方法开发过程中必须将随机特征选择纳入基线对比，并呼吁社区设计更好的特征选择评估指标，以保证改进的一致性与评估的真实性。
正文 · 原文
Abstract:Many novel unsupervised feature selection methods are proposed each year, yet their empirical evaluation is limited to supervised and unsupervised evaluation metrics computed on selected datasets, along with comparisons to existing methods. However, in the absence of an established evaluation baseline, it is difficult to determine the value added to the existing literature by each of these methods, and how effective their underlying approaches are. In this evaluation study, we are using random feature selection as a baseline for evaluating unsupervised feature selection methods. While a random selection of features might seem to be a rather weak baseline, we show in this evaluation study that many of the state-of-the-art methods in unsupervised feature selection are outperformed by random feature selection in both performance and efficiency. Accordingly, we emphasize the strict requirement of considering random feature selection as a baseline in the development process of novel unsupervised feature selection methods, and we encourage the community to develop better evaluation measures for feature selection. Both would help to ensure consistent improvement and realistic assessment.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.22973 [cs.LG] |
| (or arXiv:2605.22973v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.22973 arXiv-issued DOI via DataCite |
Submission history
From: Muhammad Rajabinasab [view email]
[v1]
Thu, 21 May 2026 19:04:54 UTC (263 KB)
[v2]
Fri, 19 Jun 2026 11:43:34 UTC (264 KB)
[v3]
Thu, 29 Oct 2026 14:34:34 UTC (22,766 KB)
来源：arXiv cs.AI · arxiv.org