2021/11/25 by Zhipeng Wang, Xiu‐Xiu Zhan, Wang, Zhipeng +5
Biochemistry, Genetics and Molecular Biology · Neuroscience · Physics and Astronomy · #Bioinformatics and Genomic Networks #Complex Network Analysis Techniques #FOS: Computer and information sciences #FOS: Physical sciences #Functional Brain Connectivity Studies #Physics and Society (physics.soc-ph) #Social and Information Networks (cs.SI)
paper · pdf · doi:10.48550/arxiv.2111.13114
openalex publication_date 2021/11/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Identifying and quantifying structural dissimilarities between complex\nnetworks is a fundamental and challenging problem in network science. Previous\nnetwork comparison methods are based on the structural features, such as the\nlength of shortest path, degree and graphlet, which may only contain part of\nthe topological information. Therefore, we propose an efficient network\ncomparison method based on network embedding, i.e., \DeepWalk, which\nconsiders the global structural information. In detail, we calculate the\ndistance between nodes through the vector extracted by \DeepWalk and\nquantify the network dissimilarity by spectral entropy based Jensen-Shannon\ndivergences of the distribution of the node distances. Experiments on both\nsynthetic and empirical data show that our method outperforms the baseline\nmethods and can distinguish networks perfectly by only using the global\nembedding based distance distribution. In addition, we show that our method can\ncapture network properties, e.g., average shortest path length and link\ndensity. Moreover, the experiments of modularity further implies the\nfunctionality of our method.\n