Frequent Sub-Structure-Based Approaches for Classifying Chemical Compounds

Frequent Sub-Structure-Based Approaches for Classifying Chemical Compounds (2003)

Cached

Download Links

[www-users.cs.umn.edu]
[www-users.cs.umn.edu]

Other Repositories/Bibliography

DBLP

by Mukund Deshpande , Michihiro Kuramochi , George Karypis

Venue:	In Proceedings of ICDM’03
Citations:	65 - 3 self

Versions

Version History

Metadata Version 3

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Frequent Sub-Structure-Based Approaches for Classifying Chemical Compounds	user correction - Legacy Corrections
AUTHOR NAME	Mukund Deshpande	user correction - Legacy Corrections
AUTHOR AFFIL	University of Minnesota, Department of Computer Science/Army HPC Research Center	user correction - Legacy Corrections
AUTHOR ADDR	Minneapolis, MN 55455	user correction - Legacy Corrections
AUTHOR NAME	Michihiro Kuramochi	user correction - Legacy Corrections
AUTHOR AFFIL	University of Minnesota, Department of Computer Science/Army HPC Research Center	user correction - Legacy Corrections
AUTHOR ADDR	Minneapolis, MN 55455	user correction - Legacy Corrections
AUTHOR NAME	George Karypis	user correction - Legacy Corrections
AUTHOR AFFIL	University of Minnesota, Department of Computer Science/Army HPC Research Center	user correction - Legacy Corrections
AUTHOR ADDR	Minneapolis, MN 55455	user correction - Legacy Corrections
ABSTRACT	In this paper we study the problem of classifying chemical compound datasets. We present a sub-structure-based classification algorithm that decouples the sub-structure discovery process from the classification model construction and uses frequent subgraph discovery algorithms to find all topological and geometric sub-structures present in the dataset. The advantage of our approach is that during classification model construction, all relevant sub-structures are available allowing the classifier to intelligently select the most discriminating ones. The computational scalability is ensured by the use of highly efficient frequent subgraph discovery algorithms coupled with aggressive feature selection. Our experimental evaluation on eight different classification problems shows that our approach is computationally scalable and outperforms existing schemes by 10% to 35%, on the average.	user correction - Legacy Corrections
YEAR	2003	INFERENCE
VENUE	In Proceedings of ICDM’03	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	35--42	INFERENCE
CITATIONS	45 found	ParsCit 1.0