Abstract | ||
---|---|---|
Algorithms that map graphs into feature vectors encoding the presence/absence of specific subgraphs, have shown excellent performance in various data mining tasks. Discriminative subgraphs have been successfully utilized as features for graphs classification. Most of the existing algorithms mine for discriminative subgraphs that completely appear frequently in graphs belonging to one class label and not so frequently in the other graphs. Graphs can be missing some edges due to noise in the data generation. In this paper, we propose a scoring function for discriminative subgraph and introduce a greedy algorithm for mining discriminative patterns. Experiment on large coexpression graphs show that the proposed approach has excellent classification performance. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/BIBM.2017.8217921 | 2017 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM) |
Keywords | DocType | ISSN |
Coexpression networks, frequent subgraphs, discriminative patterns, graph classification | Conference | 2156-1125 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bassam Qormosh | 1 | 0 | 0.34 |
Eihab El Radie | 2 | 0 | 1.01 |
Saeed Salem | 3 | 182 | 17.39 |