node2hash: Graph aware deep semantic text hashing

作者：

Highlights：

• node2hash is the first semantic text hashing model that explicitly models document and their connections.

• node2hash is an unsupervised hashing method that combines the advantage of generative modeling and deep learning.

• node2hash is applicable to datasets whose explicit connections are observed, and implicit one can be inferred.

摘要

•node2hash is the first semantic text hashing model that explicitly models document and their connections.•node2hash is an unsupervised hashing method that combines the advantage of generative modeling and deep learning.•node2hash is applicable to datasets whose explicit connections are observed, and implicit one can be inferred.

论文关键词：Semantic hashing,Variational autoencoder,Deep learning

论文评审过程：Received 28 February 2019, Revised 1 September 2019, Accepted 12 October 2019, Available online 2 November 2019, Version of Record 20 October 2020.

论文官网地址：https://doi.org/10.1016/j.ipm.2019.102143