gl2vec

• DOI: 10.1145/3341161.3342908
• Publication Date: 2020-01-15T21:07:04Z
• Authors: Kun Tu; Jian Li; Don Towsley; Dave Braines; Liam D. Turner
• Keywords: Representation; Feature (linguistics); Identification

Learning network representation has a variety of applications, such as classification. Most existing work in this area focuses on static undirected networks and does not account for presence directed edges or temporal changes. Furthermore, most node representations that do poorly tasks like In paper, we propose novel embedding methodology, gl2vec, classification both networks. gl2vec constructs vectors feature using graphlet distributions null model comparing them against random graphs. We demonstrate the efficacy usability over state-of-the-art methods type subgraph identification several real-world argue provides additional features are captured by methods, which can significantly improve their accuracy up to 10% applications.