Paper Info
Title
Modeling Collaborative Similarity with the Signed Resistance Distance Kernel
Abstract
We extend the resistance distance kernel to the domain of signed dissimilarity values, and show how it can be applied to collaborative rating prediction. The resistance distance is a graph kernel inspired by electrical network models where edges of a graph are interpreted as electrical resistances. We model the similarity between users of a large collaborative rating database using this signed resistance distance, generalizing the previously known regular resistance distance kernel which is limited to nonnegative values. We show that the signed resistance distance kernel can be computed effectively using the Moore-Penrose pseudoinverse of the Laplacian matrix of the bipartite rating graph, leading to fast computation based on the eigenvalue decomposition of the Laplacian matrix. We apply this technique to collaborative rating prediction on the Netflix Prize corpus, and show how our new kernel can replace the traditional Pearson correlation for rating prediction.
Year
DOI
Venue
2008
10.3233/978-1-58603-891-5-261
ECAI
Keywords
Field
DocType
graph kernel,electrical resistance,modeling collaborative similarity,bipartite rating graph,laplacian matrix,resistance distance kernel,resistance distance,new kernel,regular resistance distance kernel,large collaborative rating database,rating prediction,collaborative filtering,electrical network,eigenvalue decomposition,correlation matrix
Kernel (linear algebra),Graph kernel,Laplacian matrix,Mathematical optimization,Computer science,Bipartite graph,Moore–Penrose pseudoinverse,Artificial intelligence,Distance matrix,Eigendecomposition of a matrix,Resistance distance,Machine learning
Conference
Volume
ISSN
Citations 
178
0922-6389
4
PageRank 
References 
Authors
0.84
13
5
Name
Order
Citations
PageRank
Jérôme Kunegis187451.20
Stephan Schmidt240.84
sahin albayrak31298158.51
Christian Bauckhage41979195.86
Martin Mehlitz5152.52