Abstract | ||
---|---|---|
We present a method for trust prediction based on no diagonal decompositions of the asymmetric adjacency matrix of a directed network. The method we propose is based on a no diagonal decomposition into directed components (DEDICOM), which we use to learn the coefficients of a matrix polynomial of the network's adjacency matrix. We show that our method can be used to compute better low-rank approximations to a polynomial of a network's adjacency matrix than using the singular value decomposition, and that a higher precision can be achieved at the task of predicting directed links than by undirected or bipartite methods. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/ICDM.2012.16 | Data Mining |
Keywords | Field | DocType |
directed graphs,matrix decomposition,polynomial matrices,trusted computing,asymmetric adjacency matrix,bipartite methods,decomposition into directed components,directed network,low-rank approximations,matrix polynomial coefficients,network adjacency matrix,nondiagonal decompositions,singular value decomposition,trust prediction,undirected methods,decomposition into directed components,trust | Adjacency matrix,Discrete mathematics,Combinatorics,Computer science,Matrix decomposition,Symmetric matrix,Hollow matrix,Degree matrix,Diagonal matrix,Band matrix,Sparse matrix | Conference |
ISSN | ISBN | Citations |
1550-4786 | 978-1-4673-4649-8 | 5 |
PageRank | References | Authors |
0.45 | 9 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jérôme Kunegis | 1 | 874 | 51.20 |
Jörg Fliege | 2 | 210 | 20.95 |