Research Article
An Approach of Community Search with Minimum Spanning Tree Based on Node Embedding
Algorithm 1
Node embedding model NEBRW.
| Input: a network ; walks per node ; walk length ; | | windows size ; dimension | | Output: vector representations of nodes in | (1) | begin | (2) | initialize | (3) | | (4) | whiledo | (5) | foreachdo | //rw is a random walk function | (6) | | (7) | append into | (8) | end | (9) | | (10) | end | (11) | construct a corpus consisting of sentences which are stored in | (12) | use the Skip-gram to learn the mapping by treating as a corpus | (13) | return | (14) | end |
|