Combining multiple clusterings using evidence accumulation

By Ana L. N. Fred, Anil K. Jain. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005

1,260 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/5403a5c2839fad66e3f907518b11f41a56ec4e21

How researchers see this paper

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

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Evaluation of Stability of k-Means Cluster Ensembles with Respect to Random Initialization (2006, background): “One of the most successful heuristics has been randomly choosing the number of clusters assigned to each clusterer in the ensemble [ 12 ], [13], [16], [17], [21].”
Ensemble learning: A survey (2018, neutral): “Taking this approach, consensus clustering can be gained without encountering the label correspondence problem (Fred & Jain, 2005).”
Unsupervised Incremental Online Learning and Prediction of Musical Audio Signals (2015, neutral): “The expected value of R over all partition combinations P ×P is calculated as [14]: ER = 1 |C|2 ∑ A,C∈P R(A, C).”
Multi-level bootstrap analysis of stable clusters in resting-state fMRI (2009, methodology): “The key idea of the evidence accumulation algorithm (Fred and Jain, 2005) was to formulate the search for stable clusters as a clustering problem on the stability matrix.”
Ensembles for unsupervised outlier detection: challenges and research questions a position paper (2014, methodology): “, using similarity measures (again, as those available from external validity measures) or more refined methods of deriving some consensus partition [67; 19; 5; 69; 68; 21; 25; 55].”
Locally Weighted Ensemble Clustering (2016, methodology): “N M In this section, we compare the proposed LWEA and LWGP methods against eleven ensemble clustering methods, namely, CSPA [17], HGPA [17], MCLA [17], hybrid bipartite graph formulation (HBGF) [19], EAC [20], weighted connected triple based method (WCT) [23], weighted evidence accumulation clusteri”
A survey on ensemble learning (2019, background): “Fred and Jain [123] introduced the evidence accumulation clustering (EAC) concept to combine multiple clustering results, in which each partition was treated as independent evidence of data organization, and these learned partitions were combined via certain voting mechanism before adopting the hier”
Ultra-Scalable Spectral Clustering and Ensemble Clustering (2019, methodology): “1) EAC [8]: evidence accumulation clustering.”
Convex Discriminative Multitask Clustering (2013, methodology): “The most similar work with MTC in machine learning and data mining is cluster ensemble [54], [55], [56], [57], [58], [59], [60], [61], [62].”
Cluster ensembles (2011, background): “In some schemes, one does have control on how the base clusterings are produced, 6 whereas in others even this is not granted in order to allow applications involving knowledge reuse, 7 as described later.”
A Comprehensive Survey of Clustering Algorithms (2015, methodology): “(1) For the same data set, employ the same algorithm with the different parameters or the different initial conditions [85]; (2) For the same data set, employ the different algorithms [86]; (3) For the subsets, carry out the clustering respectively [86]; (4) For the same data set, carry out the clus”