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.
A Note on the Inapproximability of Correlation Clustering
University of Pennsylvania(宾夕法尼亚大学)
我们考虑相关聚类问题的不可近似性,定义如下:给定一个图$G = (V,E)$,其中每个边被标记为“+”(相似)或“-”(不相似),相关聚类试图将顶点划分为簇,以便正确地(分别)确定对的数量。不正确地)被最大化(相应地,最小化)。这两个互补的问题分别被称为MaxAgree和MinDisagree,并且已经在完全图上进行了研究,其中每个边都被标记,而一般图中某些边可能没有被标记。这两个问题的自然边加权版本也进行了研究。令S-MaxAgree表示所有权取自集合S的加权问题,我们证明了S-MaxAgree与$O(|V|^{1/2-δ})$的权在以下意义下本质上属于同一硬度类:如果存在多项式时间算法,其以高概率在因子$λ= O(\log{|V|})$内近似S-MaxAgree,则对于S '的任何选择,S ′-MaxAgree可以在多项式时间内在因子$(λ+ ε)$内近似,其中$ε> 0$可以是任意小的,具有高概率。Charikar等人的$S-MinDisagree. This result implies it is hard (assuming $ NP \neq RP $) to approximate unweighted MaxAgree within a factor of $ 80/79-ε $, improving upon a previous known factor of…