Порівняння методів

	Robust k-means	Кластеризація методом k-середніх	Спектральне кластеризація
Галузь	Машинне навчання	Машинне навчання	Машинне навчання
Родина	Machine learning	Machine learning	Machine learning
Рік появи	1999	1967 (formalized 1982)	2002
Автор методу	Garcia-Escudero, L. A. & Gordaliza, A.	MacQueen, J. B.; Lloyd, S. P.	Ng, A. Y.; Jordan, M. I.; Weiss, Y.
Тип	Robust clustering algorithm	Partitional clustering	Graph-based clustering (spectral method)
Основоположне джерело	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.	Lloyd, S. P. (1982). Least squares quantization in PCM. IEEE Transactions on Information Theory, 28(2), 129–137.	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.
Інші назви	robust k-means clustering, trimmed k-means, outlier-resistant k-means, RKM	k-means clustering, Lloyd's algorithm, k-means partitioning, hard k-means	NJW spectral clustering, graph Laplacian clustering, normalized spectral clustering, spectral graph clustering
Пов'язані	4	4	5
Підсумок	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.	K-means is a classic unsupervised partitional clustering algorithm that divides a dataset into K non-overlapping groups by iteratively assigning each observation to its nearest centroid and updating centroids as the mean of their assigned points. It is one of the most widely used exploratory tools in machine learning and data analysis.	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.