Document Hashing With Mixture-prior Generative Models

Abstract

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 o

Stats

• citations9
• S2 citations—
• github stars0
• HF likes0
• heat score7.50
• arxiv keydong2019document

Related papers

• Refining BERT Embeddings For Document Hashing Via Mutual Information Maximization (2021)3.58
• Generative Semantic Hashing Enhanced Via Boltzmann Machines (2020)3.58
• Integrating Semantics And Neighborhood Information With Graph-driven Generative Models For Document Retrieval (2021)0.00
• Variational Deep Semantic Hashing For Text Documents (2017)12.25
• Coophash: Cooperative Learning Of Multipurpose Descriptor And Contrastive Pair Generator Via Variational MCMC Teaching For Supervised Image Hashing (2022)0.00
• Deep Semantic Hashing With Generative Adversarial Networks (2018)13.50
• Pairwise Supervised Hashing With Bernoulli Variational Auto-encoder And Self-control Gradient Estimator (2020)0.00
• NASH: Toward End-to-end Neural Architecture For Generative Semantic Hashing (2018)10.07