A Graph Database Repository and Performance Evaluation Metrics for Graph Edit Distance
Graph edit distance (GED) is an error tolerant graph matching paradigm whose methods are often evaluated in a classification context and less deeply assessed in terms of the accuracy of the found solution. To evaluate the accuracy of GED methods, low level information is required not only at the classification level but also at the matching level. Most of the publicly available repositories with associated ground truths are dedicated to evaluating graph classification or exact graph matching methods and so the matching correspondences as well as the distance between each pair of graphs are not directly evaluated. This paper consists of two parts. First, we provide a graph database repository annotated with low level information like graph edit distances and their matching correspondences. Second, we propose a set of performance evaluation metrics to assess the performance of GED methods.
KeywordsGraph edit distance Performance evaluation metrics Matching correspondence
Unable to display preview. Download preview PDF.
- 2.Sorlin, S., Solnon, C., Michel Jolion, J.: A generic graph distance measure based on multivalent matchings (2007)Google Scholar
- 9.Riesen, K., Bunke, H.: IAM graph database repository for graph based pattern recognition and machine learning. In: da Vitoria Lobo, N., Kasparis, T., Roli, F., Kwok, J.T., Georgiopoulos, M., Anagnostopoulos, G.C., Loog, M. (eds.) S+SSPR 2008. LNCS, vol. 5342, pp. 287–297. Springer, Heidelberg (2008)CrossRefGoogle Scholar
- 10.Xu, K.B.: Benchmarks with hidden optimum solutions for graph problems, http://www.nlsde.buaa.edu.cn/kexu/benchmarks/graph-benchmarks.htm
- 11.Cmu house and hotel datasets, http://vasc.ri.cmu.edu/idb/html/motion
- 12.A large database of graphs and its use for benchmarking graph isomorphism algorithms 24(8), 1067 – 1079 (2003)Google Scholar
- 13.Conte, D., et al.: Challenging complexity of maximum common subgraph detection algorithms 11(1), 99–143 (2007)Google Scholar
- 14.Foggia, P., et al.: A performance comparison of five algorithms for graph isomorphism. In: IAPR TC-15, pp. 188–199 (2001)Google Scholar
- 16.Grec competition, http://symbcontestgrec05.loria.fr/index.php
- 17.Riesen, K., Bunke, H.: Graph Classification and Clustering Based on Vector Space Embedding (2010)Google Scholar
- 19.Wagner, et al.: The string-to-string correction problem 21(1), 168–173 (1974)Google Scholar
- 20.Zhou, F., De la Torre, F.: Factorized graph matching. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2012)Google Scholar
- 21.Neuhaus, M., et al.: Fast suboptimal algorithms for the computation of graph edit distance. Structural and Syntactic Pattern Recognition, 163–172 (2006)Google Scholar