Graph Classification Based on Dissimilarity Space Embedding

摘要: Recently, an emerging trend of representing objects by graphs can be observed. In fact, offer a powerful alternative to feature vectors in pattern recognition, machine learning, and related fields. However, the domain contains very little mathematical structure, consequently, there is only limited amount classification algorithms available. this paper we survey recent work on graph embedding using dissimilarity representations. Once population has been mapped vector space means procedure, all methods developed statistical recognition become directly experimental evaluation show that proposedmethodology first spaces then applying classifier significant potential outperform classifiers operate domain. Additionally, proposed framework considered contribution towards unifying domains structural recognition.