Title :
Graph-based data mining
Author :
Cook, Diane J. ; Holder, Lawrence B.
Author_Institution :
Dept. of Comput. Sci. Eng., Texas Univ., Arlington, TX, USA
Abstract :
Using databases represented as graphs, the Subdue system performs two key data mining techniques: unsupervised pattern discovery and supervised concept learning from examples. Applications to large structural databases demonstrate Subdue´s scalability and effectiveness
Keywords :
data mining; graph theory; learning by example; unsupervised learning; very large databases; Subdue system; data mining techniques; graph based data mining; large structural databases; scalability; supervised concept learning from examples; unsupervised pattern discovery; Acceleration; Assembly; Data mining; Data structures; Helium; Impedance matching; Intelligent systems; Scalability; Spatial databases; Testing;
Journal_Title :
Intelligent Systems and their Applications, IEEE
DOI :
10.1109/5254.850825
