Databases Reference
In-Depth Information
biclustering into gene expression data analysis. There are many studies on biclustering
models and methods. The notion of
-pCluster was introduced by Wang, Wang, Yang,
and Yu [WWYY02]. For informative surveys, see Madeira and Oliveira [MO04] and
Tanay, Sharan, and Shamir [TSS04]. In this chapter, we introduced the
-cluster algo-
rithm by Cheng and Church [CC00] and MaPle by Pei, Zhang, Cho, et al. [PZC
C
03]
as examples of optimization-based methods and enumeration methods for biclustering,
respectively.
Donath and Hoffman [DH73] and Fiedler [Fie73] pioneered spectral clustering. In
this chapter, we use an algorithm proposed by Ng, Jordan, and Weiss [NJW01] as an
example. For a thorough tutorial on spectral clustering, see Luxburg [Lux07].
Clustering graph and network data is an important and fast-growing topic. Schaeffer
[Sch07] provides a survey. The SimRank measure of similarity was developed by Jeh
and Widom [JW02a]. Xu et al. [XYFS07] proposed the SCAN algorithm. Arora, Rao,
and Vazirani [ARV09] discuss the sparsest cuts and approximation algorithms.
Clustering with constraints has been extensively studied. Davidson, Wagstaff, and
Basu [DWB06] proposed the measures of informativeness and coherence. The COP-
k
-means algorithm is given by Wagstaff et al. [WCRS01]. The CVQE algorithm was
proposed by Davidson and Ravi [DR05]. Tung, Han, Lakshmanan, and Ng [THLN01]
presented a framework for constraint-based clustering based on user-specified con-
straints. An efficient method for constraint-based spatial clustering in the existence of
physical obstacle constraints was proposed by Tung, Hou, and Han [THH01].
