Unsupervised Neural Generative Semantic Hashing

06/03/2019
by   Casper Hansen, et al.
0

Fast similarity search is a key component in large-scale information retrieval, where semantic hashing has become a popular strategy for representing documents as binary hash codes. Recent advances in this area have been obtained through neural network based models: generative models trained by learning to reconstruct the original documents. We present a novel unsupervised generative semantic hashing approach, Ranking based Semantic Hashing (RBSH) that consists of both a variational and a ranking based component. Similarly to variational autoencoders, the variational component is trained to reconstruct the original document conditioned on its generated hash code, and as in prior work, it only considers documents individually. The ranking component solves this limitation by incorporating inter-document similarity into the hash code generation, modelling document ranking through a hinge loss. To circumvent the need for labelled data to compute the hinge loss, we use a weak labeller and thus keep the approach fully unsupervised. Extensive experimental evaluation on four publicly available datasets against traditional baselines and recent state-of-the-art methods for semantic hashing shows that RBSH significantly outperforms all other methods across all evaluated hash code lengths. In fact, RBSH hash codes are able to perform similarly to state-of-the-art hash codes while using 2-4x fewer bits.

READ FULL TEXT

page 8

page 9

research
07/01/2020

Unsupervised Semantic Hashing with Pairwise Reconstruction

Semantic Hashing is a popular family of methods for efficient similarity...
research
03/26/2021

Unsupervised Multi-Index Semantic Hashing

Semantic hashing represents documents as compact binary vectors (hash co...
research
06/16/2020

Generative Semantic Hashing Enhanced via Boltzmann Machines

Generative semantic hashing is a promising technique for large-scale inf...
research
07/17/2020

Self-Supervised Bernoulli Autoencoders for Semi-Supervised Hashing

Semantic hashing is an emerging technique for large-scale similarity sea...
research
06/02/2021

Self-Supervised Document Similarity Ranking via Contextualized Language Models and Hierarchical Inference

We present a novel model for the problem of ranking a collection of docu...
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
12/16/2014

Random Forests Can Hash

Hash codes are a very efficient data representation needed to be able to...

Please sign up or login with your details

Forgot password? Click here to reset