Yuanyuan Zhu
Jeffrey Xu Yu
ABSTRACT
A graph models complex structural relationships among objects, and has been prevalently used in a wide range of applications. Building an automated graph classification model becomes very important for predicting unknown graphs or understanding complex structures between different classes. The graph classification framework being widely used consists of two steps, namely, feature selection and classification. The key issue is how to select important subgraph features from a graph database with a large number of graphs including positive graphs and negative graphs. Given the features selected, a generic classification approach can be used to build a classification model. In this paper, we focus on feature selection. We identify two main issues with the most widely used feature selection approach which is based on a discriminative score to select frequent subgraph features, and introduce a new diversified discriminative score to select features that have a higher diversity. We analyze the properties of the newly proposed diversified discriminative score, and conducted extensive performance studies to demonstrate that such a diversified discriminative score makes positive/negative graphs separable and leads to a higher classification accuracy.
- D. Bandyopadhyay, J. Huan, J. Liu, J. Prins, J. Snoeyink, W. Wang, and A. Tropsha. Structure-based function inference using protein family-specific fingerprints. Protein Science, 15(6):1537--1543, 2006.Google Scholar
Cross Ref
- C.-C. Chang and C.-J. Lin. Libsvm: A library for support vector machines, 2001. software available at http://www.csie.ntu.edu.tw/cjlin/libsvm.Google Scholar
- C. Chen, C. X. Lin, M. Fredrikson, M. Christodorescu, X. Yan, and J. Han. Mining graph patterns efficiently via randomized summaries. PVLDB, 2(1):742--753, 2009. Google ScholarDigital Library
- H. Cheng, X. Yan, J. Han, and C.-W. Hsu. Discriminative frequent pattern analysis for effective classification. In ICDE, pages 716--725, 2007.Google ScholarCross Ref
- M. Deshpande, M. Kuramochi, N. Wale, and G. Karypis. Frequent substructure-based approaches for classifying chemical compounds. TKDE, 17(8):1036--1050, 2005. Google ScholarDigital Library
- F. Fleuret. Fast binary feature selection with conditional mutual information. JMLR, 5:1531--1555, 2004. Google ScholarDigital Library
- J. Han, J. Wang, Y. Lu, and P. Tzvetkov. Mining top-k frequent closed patterns without minimum support. In ICDM, pages 211--218, 2002. Google ScholarDigital Library
- M. A. Hasan and M. J. Zaki. Output space sampling for graph patterns. PVLDB, 2(1):730--741, 2009. Google ScholarDigital Library
- J. Huan, W. Wang, and J. Prins. Efficient mining of frequent subgraphs in the presence of isomorphism. In ICDM, pages 549--552, 2003. Google ScholarDigital Library
- J. Huan, W. Wang, J. Prins, and J. Yang. Spin: mining maximal frequent subgraphs from graph databases. In KDD, pages 581--586, 2004. Google ScholarDigital Library
- N. Jin, C. Young, and W. Wang. Graph classification based on pattern co-occurrence. In CIKM, pages 573--582, 2009. Google ScholarDigital Library
- N. Jin, C. Young, and W. Wang. Gaia: graph classification using evolutionary computation. In SIGMOD, pages 879--890, 2010. Google ScholarDigital Library
- M. Kuramochi and G. Karypis. Frequent subgraph discovery. In ICDM, pages 313--320, 2001. Google ScholarDigital Library
- S. Nijssen and J. N. Kok. A quickstart in frequent structure mining can make a difference. In KDD, pages 647--652, 2004. Google ScholarDigital Library
- H. Peng, F. Long, and C. H. Q. Ding. Feature selection based on mutual information: Criteria of max-dependency, max-relevance, and min-redundancy. TPAMI, 27(8):1226--1238, 2005. Google ScholarDigital Library
- S. Ranu and A. K. Singh. Graphsig: A scalable approach to mining significant subgraphs in large graph databases. In ICDE, pages 844--855, 2009. Google ScholarDigital Library
- H. Saigo, N. Krämer, and K. Tsuda. Partial least squares regression for graph mining. In KDD, pages 578--586, 2008. Google ScholarDigital Library
- M. Thoma, H. Cheng, A. Gretton, J. Han, H. Kriegel, A. Smola, L. Song, P. Yu, X. Yan, and K. Borgwardt. Near-optimal supervised feature selection among frequent subgraphs. In SDM, 2009.Google ScholarCross Ref
- J. Weston, S. Mukherjee, O. Chapelle, M. Pontil, T. Poggio, and V. Vapnik. Feature selection for svms. NIPS, pages 668--674, 2001.Google Scholar
- X. Yan, H. Cheng, J. Han, and P. S. Yu. Mining significant graph patterns by leap search. In SIGMOD, pages 433--444, 2008. Google ScholarDigital Library
- X. Yan and J. Han. gspan: Graph-based substructure pattern mining. In ICDM, pages 721--724, 2002. Google ScholarDigital Library
- X. Yan and J. Han. Closegraph: mining closed frequent graph patterns. In KDD, pages 286--295, 2003. Google ScholarDigital Library
- S. Zhang, J. Yang, and V. Cheedella. Monkey: Approximate graph mining based on spanning trees. In ICDE, pages 1247--1249, 2007.Google ScholarCross Ref
- L. Zhu, W. K. Ng, and S. Han. Classifying graphs using theoretical metrics: A study of feasibility. In DASFAA, 2011. Google ScholarDigital Library
Index Terms
- Graph classification: a diversified discriminative feature selection approach
Recommendations
Semi-supervised feature selection for graph classification
KDD '10: Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data miningThe problem of graph classification has attracted great interest in the last decade. Current research on graph classification assumes the existence of large amounts of labeled training graphs. However, in many applications, the labels of graph data are ...
Positive and Unlabeled Learning for Graph Classification
ICDM '11: Proceedings of the 2011 IEEE 11th International Conference on Data MiningThe problem of graph classification has drawn much attention in the last decade. Conventional approaches on graph classification focus on mining discriminative sub graph features under supervised settings. The feature selection strategies strictly follow ...
Multi-label Feature Selection for Graph Classification
ICDM '10: Proceedings of the 2010 IEEE International Conference on Data MiningNowadays, the classification of graph data has become an important and active research topic in the last decade, which has a wide variety of real world applications, e.g. drug activity predictions and kinase inhibitor discovery. Current research on ...
Comments