Data clustering: a review

By Anil K. Jain, M. Murty, Patrick J. Flynn. 1999

How researchers see this paper

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

In Model Architectures

Citations in the corpus

Towards the Science of Security and Privacy in Machine Learning (2016, background): “Unsupervised learning considers problems such as clustering points according to a similarity metric [7], dimensionality reduction to project data in lower dimensional subspaces [8], and model pre-training [10].”
Poisoning behavioral malware clustering (2014, background): “Before describing the heuristics for poisoning the single-linkage clustering algorithm, it is worth pointing out that this algorithm, as any other variant of hierarchical clustering, outputs a hierarchy of clusterings [19].”
A survey of data fusion in smart city applications (2019, methodology): “Examples of such methods involves clustering [72], anomaly detection [73] and others [38].”
Simpson's Paradox in COVID-19 Case Fatality Rates: A Mediation Analysis of Age-Related Causal Effects (2020, background): “sions can be reached depending on how the data are aggregated or stratified, it also has close connections to clustering [39], [40], another core AI technique, which is especially challenging for”
SoK: Security and Privacy in Machine Learning (2018, background): “This includes problems such as clustering points according to a similarity metric [9], dimensionality reduction to project data in lower dimensional subspaces [10], and model pre-training [11].”
Joint Unsupervised Learning of Deep Representations and Image Clusters (2016, methodology): “We compare our approach with 12 clustering algorithms, including K-means [36], NJW spectral clustering (SCNJW) [40], self-tuning spectral clustering (SC-ST)[61], large-scale spectral clustering (SC-LS) [3], agglomerative clustering with average linkage (AC-Link)[24], Zeta function based agglomerativ”
Distance geometry and data science (2019, background): “ar, this very simple analysis oers no guarantee on the approximation of the objective function. For more information on the k-means algorithm, see [30]. k-means is an unsupervised learning technique [92], insofar as it does not rest on a data model with parameters to be estimated prior to actually n”
Flow map layout (2005, methodology): “We use an agglomerative hierarchical clustering [9] that creates a binary tree from the input set of nodes.”
A Mixture Model for Clustering Ensembles (2004, background): “Data clustering is a difficult inverse problem, and as such is ill-posed when prior information about the underlying data distributions is not well defined [15, 16, 21].”
LOCI: fast outlier detection using the local correlation integral (2003, background): “The salient approaches to outlier detection can be classified as either distribution-based [5], depthbased [16], clustering [14], distance-based [17, 20, 18, 19], or density-based [8] (see Section 2).”
Machine Learning in Financial Crisis Prediction: A Survey (2012, background): “The second purpose is to identify classes of patterns for subsequent supervised classification [60].”
Deep Image Category Discovery using a Transferred Similarity Function (2016, background): “Clustering-based unsupervised learning approaches can be traditionally posed as a two-stage solution: learning a feature embedding [7] and clustering based on certain metrics [17][22][12][2].”
A Descriptive Framework for the Field of Data Mining and Knowledge Discovery (2008, methodology): “For a comprehensive review of these algorithms and applications, refer to [Jain et al. 1999; Zhao and Karypis 2003].”
Self-Supervised Learning in Remote Sensing: A review (2022, background): “Traditional unsupervised algorithms tend to utilize the statistics of the input data and generate groups by dimensionality reduction [37], [38] or clustering [39].”
The Effectiveness of Lloyd-Type Methods for the k-Means Problem (2006, background): “This and similar iterative descent methods soon became the dominant approaches to the problem [35, 33, 12, 31] (see also [19, 20, 24] and the references therein); they remain so today, and are still being improved [1, 40, 42, 28].”