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

arXiv: https://arxiv.org/abs/1805.05361 · HTML: https://mlsanity.com/paper/1805.05361/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2018.

## Built on by (most cited first, 11 of 11)

- [Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders](https://mlsanity.com/paper/2210.12316/) (2022)
- [Unsupervised Hashing with Contrastive Information Bottleneck](https://mlsanity.com/paper/2105.06138/) (2021)
- [VAE Approximation Error: ELBO and Exponential Families](https://mlsanity.com/paper/2102.09310/) (2021)
- [Unsupervised Multi-Index Semantic Hashing](https://mlsanity.com/paper/2103.14460/) (2021)
- [Projected Hamming Dissimilarity for Bit-Level Importance Coding in Collaborative Filtering](https://mlsanity.com/paper/2103.14455/) (2021)
- [Bias-Variance Tradeoffs in Single-Sample Binary Gradient Estimators](https://mlsanity.com/paper/2110.03549/) (2021)
- [Learning Discrete Structured Variational Auto-Encoder using Natural Evolution Strategies](https://mlsanity.com/paper/2205.01324/) (2022)
- [Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings](https://mlsanity.com/paper/2609.03376/) (2026)
- [Advances in Electron Microscopy with Deep Learning](https://mlsanity.com/paper/2101.01178/) (2021)
- [Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval](https://mlsanity.com/paper/2105.13066/) (2021)
- [Learning Similarity Preserving Binary Codes for Recommender Systems](https://mlsanity.com/paper/2204.08569/) (2022)

## Abstract (arXiv)

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.