Paper Info
Title
Maximum Common Subgraph based locally weighted regression
Abstract
This paper investigates a simple, yet effective method for regression on graphs, in particular for applications in chem-informatics and for quantitative structure-activity relationships (QSARs). The method combines Locally Weighted Learning (LWL) with Maximum Common Subgraph (MCS) based graph distances. More specifically, we investigate a variant of locally weighted regression on graphs (structures) that uses the maximum common subgraph for determining and weighting the neighborhood of a graph and feature vectors for the actual regression model. We show that this combination, LWL-MCS, outperforms other methods that use the local neighborhood of graphs for regression. The performance of this method on graphs suggests it might be useful for other types of structured data as well.
Year
DOI
Venue
2012
10.1145/2245276.2245309
SAC
Keywords
Field
DocType
quantitative structure-activity relationship,weighted regression,local neighborhood,actual regression model,effective method,structured data,maximum common subgraph,feature vector,graph distance,regression,quantitative structure activity relationship,clustering,regression model,bioinformatics,applications
Feature vector,Combinatorics,Weighting,Regression,Pattern recognition,Regression analysis,Computer science,Lazy learning,Local regression,Artificial intelligence,Cluster analysis,Data model
Conference
Citations 
PageRank 
References 
0
0.34
13
Authors
4
Name
Order
Citations
PageRank
Madeleine Seeland1273.38
Fabian Buchwald2474.65
Stefan Kramer31313141.90
Bernhard Pfahringer410252494.74