方法对比

	鲁棒k均值	DBSCAN	层次聚类	谱聚类
领域	机器学习	机器学习	机器学习	机器学习
方法族	Machine learning	Machine learning	Machine learning	Machine learning
起源年份	1999	1996	1963	2002
提出者	Garcia-Escudero, L. A. & Gordaliza, A.	Ester, M., Kriegel, H.-P., Sander, J. & Xu, X.	Ward, J. H.	Ng, A. Y.; Jordan, M. I.; Weiss, Y.
类型	Robust clustering algorithm	Density-based clustering algorithm	Unsupervised clustering (agglomerative)	Graph-based clustering (spectral method)
开创性文献	Garcia-Escudero, L. A., & Gordaliza, A. (1999). Robustness properties of k-means and trimmed k-means. Journal of the American Statistical Association, 94(447), 956–969.	Ester, M., Kriegel, H.-P., Sander, J. & Xu, X. (1996). A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise. Proceedings of the 2nd KDD, 226–231.	Ward, J. H. (1963). Hierarchical Grouping to Optimize an Objective Function. Journal of the American Statistical Association, 58(301), 236–244.	Ng, A. Y., Jordan, M. I., & Weiss, Y. (2002). On Spectral Clustering: Analysis and an Algorithm. Advances in Neural Information Processing Systems, 14, 849–856.
别名	robust k-means clustering, trimmed k-means, outlier-resistant k-means, RKM	DBSCAN Kümeleme, density-based clustering, density-based spatial clustering	Hiyerarşik Kümeleme, hiyerarşik kümeleme, agglomerative clustering, hierarchical agglomerative clustering	NJW spectral clustering, graph Laplacian clustering, normalized spectral clustering, spectral graph clustering
相关	4	3	4	5
摘要	Robust k-means is a variant of classical k-means clustering designed to resist the influence of outliers. By trimming a specified fraction of the most extreme observations before computing cluster centers, it produces stable and meaningful partitions even when the data contain noise, contamination, or heavy-tailed distributions — situations where standard k-means breaks down.	DBSCAN is a density-based clustering algorithm, introduced by Ester, Kriegel, Sander and Xu in 1996, that groups together points lying in dense regions and flags points in sparse regions as noise. It is effective on noisy data and on clusters of irregular, non-spherical shapes.	Hierarchical clustering is an unsupervised method that groups observations into nested clusters and draws the result as a dendrogram, so the number of clusters need not be fixed in advance. Its agglomerative form rests on the objective-function grouping criterion introduced by Joe Ward in 1963.	Spectral Clustering is a graph-based unsupervised learning algorithm, formalized by Ng, Jordan, and Weiss in 2002, that maps data points into a low-dimensional eigenspace derived from the similarity graph's Laplacian before applying k-means. This spectral embedding makes it possible to recover clusters of arbitrary shape — rings, crescents, interleaved spirals — that Euclidean distance-based methods consistently fail to separate.