arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.03782cs.LGstat.ML
收藏

聚类算法评价的一个重要注记

A Critical Note on the Evaluation of Clustering Algorithms

International Graduate School of Tsinghua University(清华大学国际研究生院);Tsinghua University(清华大学)

Tiantian Zhang, Li Zhong, Bo Yuan

摘要:

实验评估是研究聚类算法和许多其他机器学习算法的主要研究方法论。为此,一些基准数据集已被广泛用于文献中,其质量对研究工作的价值起着关键作用。然而,在大多数现有的研究中,很少关注的数据集的属性,他们往往被视为黑箱问题。例如,在聚类研究中,通常使用用于分类的数据集,并假设类标签作为判断聚类质量的基础事实。在我们的工作中,先进的可视化和降维技术的帮助下,我们表明,这种做法可能会严重损害研究质量和产生误导性的结果。我们建议,现有的基准数据集的适用性应仔细重新审视和显着的努力,需要致力于改善目前的实践中的聚类算法的实验评估,以确保算法和问题之间的基本匹配。

英文摘要:

Experimental evaluation is a major research methodology for investigating clustering algorithms and many other machine learning algorithms. For this purpose, a number of benchmark datasets have been widely used in the literature and their quality plays a key role on the value of the research work. However, in most of the existing studies, little attention has been paid to the properties of the datasets and they are often regarded as black-box problems. For example, it is common to use datasets intended for classification in clustering research and assume class la-bels as the ground truth for judging the quality of cluster-ing. In our work, with the help of advanced visualization and dimension reduction techniques, we show that this practice may seriously compromise the research quality and produce misleading results. We suggest that the applicability of existing benchmark datasets should be carefully revisited and significant efforts need to be devoted to improving the current practice of experimental evaluation of clustering algorithms to ensure an essential match between algorithms and problems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑