ABSTRACT
In Chapter 2, we presented a new co-clustering framework, Block Value Decomposition (BVD), for bi-type heterogeneous relational data, which factorizes the relational data matrix into three components the row-coefficient matrix R, the block value matrix B, and the column-coefficient matrix C. In this chapter, under BVD framework, we focus on a special yet very popular case-nonnegative relational data, and propose a specific novel co-clustering algorithm that iteratively computes the three decomposition matrices based on the multiplicative updating rules.
