Constructing Treatment Portfolios Using Affinity Propagation

Dueck, Delbert; Frey, Brendan J.; Jojić, Nebojša; Jojic, Vladimir; Giaever, Guri; Emili, Andrew; Musso, Gabriel; Hegele, Robert A.

doi:10.1007/978-3-540-78839-3_31

Cited by 31 publications

(16 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For point i, the value k that maximizes a(i, k) + r(i, k) identifies point i as exemplar if k=i or identifies the data point that is the exemplars for point i. In other words, as suggested in [5], after exchanging messages, Affinity Propagation identifies a set of exemplars K so as to maximize the net similarity, which is defined by the authors as…”

Section: Methodsmentioning

confidence: 99%

Cancer profiles by affinity propagation

Soria

Garibaldi

Ambrogi

et al. 2009

IJKESDP

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Cancer profiles by affinity propagation

Soria

Garibaldi

Ambrogi

et al. 2009

IJKESDP

View full text Add to dashboard Cite

show abstract

“…The solution, however, relies on solving a knapsack problem as an intermediate step. Since AP can be easily transformed to represent the facility location problem (Dueck et al, 2008), the CAP formulation can also be transformed to give an algorithm for solving the well-known capacitated facility location problem (Sridharan, 1995). Finally, the hard limit on L used here can be replaced with a cost that increases as cluster size increases.…”

Section: Deriving Message Updates For Capacitated Affinity Propagationmentioning

confidence: 99%

A Binary Variable Model for Affinity Propagation

2009

Self Cite

View full text Add to dashboard Cite

Affinity propagation (AP) was recently introduced as an unsupervised learning algorithm for exemplar-based clustering. We present a derivation of AP that is much simpler than the original one and is based on a quite different graphical model. The new model allows easy derivations of message updates for extensions and modifications of the standard AP algorithm. We demonstrate this by adjusting the new AP model to represent the capacitated clustering problem. For those wishing to investigate or extend the graphical model of the AP algorithm, we suggest using this new formulation since it allows a simpler and more intuitive model manipulation.

show abstract

“…Dueck and Frey [15] applied a translation-invariant nonmetric similarity to AP in 2007, which achieved a much lower reconstruction error and classification error rate in Olivetti face data set. In 2008, Dueck et al [16] modified AP and applied it to a subset selection of yeast genes that act as a drug-response footprint and a subset clustering of vaccine sequences that provided maximum epitope coverage for an HIV genome population. It is declared and demonstrated that AP performs well and was widely used in [10,[14][15][16].…”

Section: Related Workmentioning

confidence: 99%

Proper Global Shared Preference Detection Based on Golden Section and Genetic Algorithm for Affinity Propagation Clustering

Jiao

Bie

Zhang

et al. 2016

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Affinity propagation (AP) clustering is a well-known effective clustering algorithm that outperforms other traditional clustering algorithms. However, the quality of clustering results depends considerably on related sensitive parameters (i.e., preferences and the damping factor). Thus, a feasible procedure based on golden section (GS) and the genetic algorithm (GA) is proposed. This procedure, called the "GS/GA-AP" algorithm, can perform proper global shared preference detection, including identifying a suitable number of clusters. A global shared preference is provided using the GS value between the minimum and maximum of similarities for AP as a default option, and the unsatisfactory clustering result becomes robust when the parameter with GA is selected. Finally, satisfactory experiments using one simulation data set and eight benchmark data sets are performed to verify the effectiveness of the proposed algorithm. The results indicate that GS/GA-AP clearly outperforms the original AP clustering algorithm.

show abstract

Constructing Treatment Portfolios Using Affinity Propagation

Cited by 31 publications

References 7 publications

Cancer profiles by affinity propagation

Cancer profiles by affinity propagation

A Binary Variable Model for Affinity Propagation

Proper Global Shared Preference Detection Based on Golden Section and Genetic Algorithm for Affinity Propagation Clustering

Contact Info

Product

Resources

About