NASH: Toward End-to-end Neural Architecture For Generative Semantic Hashing

Abstract

Semantic hashing has become a powerful paradigm for fast similarity search in many information retrieval systems. While fairly successful, previous techniques generally require two-stage training, and the binary constraints are handled ad-hoc. In this paper, we present an end-to-end Neural Architecture for Semantic Hashing (NASH), where the binary hashing codes are treated as Bernoulli latent variables. A neural variational inference framework is proposed for training, where gradients are directly back-propagated through the discrete latent variable to optimize the hash function. We also draw connections between proposed method and rate-distortion theory, which provides a theoretical foundation for the effectiveness of the proposed framework. Experimental results on three public datasets demonstrate that our method significantly outperforms several state-of-the-art models on both unsupervised and supervised scenarios.

Stats

• citations21
• S2 citations—
• github stars0
• HF likes0
• heat score10.07
• arxiv keyshen2018nash

Related papers

• Self-supervised Bernoulli Autoencoders For Semi-supervised Hashing (2020)3.66
• 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
• Variational Deep Semantic Hashing For Text Documents (2017)12.25
• Generative Semantic Hashing Enhanced Via Boltzmann Machines (2020)3.58
• Unsupervised Semantic Deep Hashing (2018)10.48
• Supervised Hashing With End-to-end Binary Deep Neural Network (2017)2.26
• Codebook-centric Deep Hashing: End-to-end Joint Learning Of Semantic Hash Centers And Neural Hash Function (2025)0.00