Structural Pattern Recognition with Graph Edit Distance : Approximation Algorithms and Applications / / by Kaspar Riesen

• Autore: Riesen Kaspar
• Pubblicazione: Cham : , : Springer International Publishing : , : Imprint : Springer, , 2015
• Edizione: 1st ed. 2015.
• Descrizione fisica: 1 online resource (164 p.)
• Disciplina: 006.4
• Soggetto topico: Pattern recognition systems; Artificial intelligence - Data processing; Automated Pattern Recognition; Data Science
• Note generali: Description based upon print version of record.
• Nota di bibliografia: Includes bibliographical references at the end of each chapters and index.
• Nota di contenuto: Preface; Acknowledgments; Contents; Part I Foundations and Applicationsof Graph Edit Distance; 1 Introduction and Basic Concepts; 1.1 Pattern Recognition; 1.1.1 Statistical and Structural Pattern Recognition; 1.2 Graph and Subgraph; 1.3 Graph Matching; 1.3.1 Exact Graph Matching; 1.3.2 Error-Tolerant Graph Matching; 1.4 Outline of the Book; References; 2 Graph Edit Distance; 2.1 Basic Definition and Properties; 2.1.1 Conditions on Edit Cost Functions; 2.1.2 Example Definitions of Cost Functions; 2.2 Computation of Exact Graph Edit Distance; 2.3 Graph Edit Distance-Based Pattern Recognition ; 2.3.1 Nearest-Neighbor Classification2.3.2 Kernel-Based Classification; 2.3.3 Classification of Vector Space Embedded Graphs; References; 3 Bipartite Graph Edit Distance; 3.1 Graph Edit Distance as Quadratic Assignment Problem; 3.2 Bipartite Graph Edit Distance; 3.2.1 Deriving Upper and Lower Bounds on the Graph Edit Distance; 3.2.2 Summary; 3.3 Experimental Evaluation; 3.4 Pattern Recognition Applications of Bipartite Graph Edit Distance; References; Part II Recent Developments and Researchon Graph Edit Distance; 4 Improving the Distance Accuracy of Bipartite Graph Edit Distance ; 4.1 Change of Notation4.2 Improvements via Search Strategies; 4.2.1 Iterative Search; 4.2.2 Floating Search; 4.2.3 Genetic Search; 4.2.4 Greedy Search; 4.2.5 Genetic Search with Swap Strategy; 4.2.6 Beam Search; 4.2.7 Experimental Evaluation; 4.3 Improvements via Integration of Node Centrality Information; 4.3.1 Node Centrality Measures; 4.3.2 Integrating Node Centrality in the Assignment; 4.3.3 Experimental Evaluation; References; 5 Learning Exact Graph Edit Distance; 5.1 Predicting Exact Graph Edit Distance from Lower and Upper Bounds; 5.1.1 Linear Support Vector Regression ; 5.1.2 Nonlinear Support Vector Regression5.1.3 Predicting d λmin from dψ and d' ψ; 5.1.4 Experimental Evaluation; 5.2 Predicting the Correctness of Node Edit Operations; 5.2.1 Features for Node Edit Operations; 5.2.2 Experimental Evaluation; References; 6 Speeding Up Bipartite Graph Edit Distance; 6.1 Suboptimal Assignment Algorithms; 6.1.1 Basic Greedy Assignment; 6.1.2 Tie Break Strategy; 6.1.3 Refined Greedy Assignment; 6.1.4 Greedy Assignment Regarding Loss; 6.1.5 Order of Node Processing; 6.1.6 Greedy Sort Assignment; 6.2 Relations to Exact Graph Edit Distance ; 6.3 Experimental EvaluationReferences; 7 Conclusions and Future Work; 7.1 Main Contributions and Findings; 7.2 Future Work; References; 8 Appendix A: Experimental Evaluation of Sorted Beam Search; 8.1 Sorting Criteria; 8.1.1 Confident; 8.1.2 Unique; 8.1.3 Divergent; 8.1.4 Leader; 8.1.5 Interval; 8.1.6 Deviation; 8.2 Experimental Evaluation; References; 9 Appendix B: Data Sets; 9.1 LETTER Graphs; 9.2 GREC Graphs; 9.3 FP Graphs; 9.4 AIDS Graphs; 9.5 MUTA Graphs; 9.6 PROT Graphs; 9.7 GREYC Graphs; References; Index
• Sommario/riassunto: This unique text/reference presents a thorough introduction to the field of structural pattern recognition, with a particular focus on graph edit distance (GED), one of the most flexible graph distance models available. The book also provides a detailed review of a diverse selection of novel methods related to GED, and concludes by suggesting possible avenues for future research. Topics and features: Formally introduces the concept of GED, and highlights the basic properties of this graph matching paradigm Describes a reformulation of GED to a quadratic assignment problem Illustrates how the quadratic assignment problem of GED can be reduced to a linear sum assignment problem Reviews strategies for reducing both the overestimation of the true edit distance and the matching time in the approximation framework Examines the improvement demonstrated by the described algorithmic framework with respect to the distance accuracy and the matching time Includes appendices listing the datasets employed for the experimental evaluations discussed in the book Researchers and graduate students interested in the field of structural pattern recognition will find this focused work to be an essential reference on the latest developments in GED. Dr. Kaspar Riesen is a university lecturer of computer science in the Institute for Information Systems at the University of Applied Sciences and Arts Northwestern Switzerland, Olten, Switzerland.
• Titolo autorizzato: Structural Pattern Recognition with Graph Edit Distance
• ISBN: 3-319-27252-7
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910298963203321
• Lo trovi qui: Univ. Federico II
• Serie: Advances in Computer Vision and Pattern Recognition, . 2191-6594