Document Hashing with Mixture-Prior Generative Models

08/29/2019
by   Wei Dong, et al.
0

Hashing is promising for large-scale information retrieval tasks thanks to the efficiency of distance evaluation between binary codes. Generative hashing is often used to generate hashing codes in an unsupervised way. However, existing generative hashing methods only considered the use of simple priors, like Gaussian and Bernoulli priors, which limits these methods to further improve their performance. In this paper, two mixture-prior generative models are proposed, under the objective to produce high-quality hashing codes for documents. Specifically, a Gaussian mixture prior is first imposed onto the variational auto-encoder (VAE), followed by a separate step to cast the continuous latent representation of VAE into binary code. To avoid the performance loss caused by the separate casting, a model using a Bernoulli mixture prior is further developed, in which an end-to-end training is admitted by resorting to the straight-through (ST) discrete gradient estimator. Experimental results on several benchmark datasets demonstrate that the proposed methods, especially the one using Bernoulli mixture priors, consistently outperform existing ones by a substantial margin.

READ FULL TEXT
research
05/21/2020

Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator

Semantic hashing has become a crucial component of fast similarity searc...
research
09/07/2021

Refining BERT Embeddings for Document Hashing via Mutual Information Maximization

Existing unsupervised document hashing methods are mostly established on...
research
04/06/2017

Enhance Feature Discrimination for Unsupervised Hashing

We introduce a novel approach to improve unsupervised hashing. Specifica...
research
05/27/2021

Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval

With the need of fast retrieval speed and small memory footprint, docume...
research
05/19/2017

VAE with a VampPrior

Many different methods to train deep generative models have been introdu...
research
02/27/2020

Auto-Encoding Twin-Bottleneck Hashing

Conventional unsupervised hashing methods usually take advantage of simi...
research
05/14/2018

NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing

Semantic hashing has become a powerful paradigm for fast similarity sear...

Please sign up or login with your details

Forgot password? Click here to reset