Direct Clustering of a Data Matrix

By John Hartigan. 1972

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

Invariant Information Clustering for Unsupervised Image Classification and Segmentation (2018, background): “More generally, learning from paired data has been explored in co-clustering [25, 16] and in other works [50] that build on the information bottleneck principle [20].”
Data clustering: 50 years beyond K-means (2008, unknown): “This problem was first studied under the name direct clustering by Hartigan (1972).”
Biclustering of Expression Data (2000, methodology): “Hartigan (1972) also mentioned that the criterion for partitioning may be other than a constant value, for example, a two-way analysis of variance model, which is quite similar to the mean squared residue scoring proposed in this article.”
Information-theoretic co-clustering (2003, methodology): “There was some early work on co-clustering, such as in [11] which used a local greedy splitting procedure to identify hierarchical row and column clusters in matrices of small size.”
Clustering high-dimensional data: A survey on subspace clustering, pattern-based clustering, and correlation clustering (2009, methodology): “…and Meulman 2004] DOC [Procopiuc et al. 2002] DiSH [Achtert et al. 2007] FIRES [Kriegel et al. 2005] pattern-based clustering Block clustering [Hartigan 1972] n a δ-bicluster [Cheng and Church 2000] n a FLOC [Yang et al. 2002] n a p-Cluster [Wang et al. 2002] n a MaPle [Pei et al. 2003] n a…”
Extracting Conserved Gene Expression Motifs from Gene Expression Data (2002, background): “Hartigan’s block clustering algorithm 13 ; 10 repeatedly rearranges the rows and columns of the matrix of gene expression values so that the rearranged matrix contains several disjoint blocks (contiguous sub-matrices) of highly correlated values.”
Label-free, normalized quantification of complex mass spectrometry data for proteomics analysis (2009, unknown): “A two-way clustering was performed, which is a data mining technique that allows simultaneous clustering of the rows and columns of a matri”
From big data analysis to personalized medicine for all: challenges and opportunities (2015, background): “Other similar, but conceptually different approaches include generalized singular value decomposition [91], and integrative bioclustering methods [92, 93].”
Biclustering in data mining (2008, methodology): “Apparently the earliest biclustering algorithm that may be found in the literature is so-called direct clustering by Hartigan [18] also known as block clustering .”
Clustering-based short-term load forecasting for residential electricity under the increasing-block pricing tariffs in China (2018, methodology): “In this study, the Euclidean distance [21, 24] is used to measure the difference of consumption behaviours between two consumers.”
Kernel Methods and Machine Learning (2014, background): “Basic bi-cluster criterion: constant-value matrix norm Hartigan [92] proposed a constant-value matrix norm that has a very broad application spectrum.”
Optimal rates of statistical seriation (2016, background): “Actually, in his seminal work on clustering, Hartigan [42] advocates for a post-processing of direct clustering with seriation for better data visualization.”
Density‐based clustering (2019, background): “Another natural motivation is often found in zoology (Carmichael, George, & Julius, 1968; Hartigan, 1972).”
Text Mining Infrastructure in R (2008, methodology): “Hierarchical clustering Here we show hierarchical clustering (Johnson 1967; Hartigan 1975; Anderberg 1973; Hartigan 1972) with text documents.”
Biclustering algorithms for biological data analysis: a survey (2004, unknown): “The basic algorithm for forward block splitting was due to Hartigan [13] who called it direct clustering (see Section III-B).”
A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists (2017, methodology): “Coclustering is a technique to consider two dimensions while doing clustering (Hartigan, 1972; Pontes et al., 2015).”
Statistical debugging: simultaneous identification of multiple bugs (2006, methodology): “We approach the problem from the perspective of bi-clustering (see, e.g., Dhillon, 2001; Hartigan, 1972).”
Cluster analysis for gene expression data: a survey (2004, methodology): “These observations induced a series of approaches based on block clustering [Hartigan1972], where “block” in those approaches means a subset of genes with coherent expression of patterns and large variation across a subset of samples.”