Furthermore, this article proposes a principle ofdesigning community detection algorithm (the principle which states therelationship among algorithms, benchmarks and the reality of communitypartition) and offers the details about designing model. Depending on therecommendeddesigningmodel, thisarticleproposesa relativelynewmethod todemonstrate how to devise and improve detection algorithms flexibly using theproposed model. Some test results showing the effect of CNM and proposedalgorithm are also provided in our tests, including a trial on a real small-scalenetworkandtestsonartificialnetworks.
Keywords community detection, community partition, clustering algorithm, agglomerating method, algorithm analysis
