Abstract | ||
---|---|---|
Network embedding based on the random walk and skip-gram model such as the DeepWalk and Node2Vec algorithms have received wide attention. We identify that these algorithms essentially estimate the node similarities by random walk simulation, which is unreliable, inefficient, and inflexible. We propose to explicitly use node similarity measures instead of random walk simulation. Based on this strategy and a new proposed similarity measure, we present a fast and scalable algorithm AA(+)Emb. Experiments show that AA(+)Emb outperforms state-of-the-art network embedding algorithms on several commonly used benchmark networks. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1007/978-3-319-97304-3_33 | PRICAI 2018: TRENDS IN ARTIFICIAL INTELLIGENCE, PT I |
Field | DocType | Volume |
Similarity measure,Pattern recognition,Computer science,Random walk,Algorithm,Artificial intelligence,Scalable algorithms,Network embedding | Conference | 11012 |
ISSN | Citations | PageRank |
0302-9743 | 1 | 0.34 |
References | Authors | |
18 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xin Liu | 1 | 104 | 15.16 |
Natthawut Kertkeidkachorn | 2 | 5 | 8.54 |
Tsuyoshi Murata | 3 | 37 | 14.01 |
Kyoung-Sook Kim | 4 | 24 | 14.07 |
Julien Leblay | 5 | 92 | 9.98 |
Steven Lynden | 6 | 19 | 2.19 |