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

arXiv: https://arxiv.org/abs/2105.13066 · HTML: https://mlsanity.com/paper/2105.13066/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 34 references that are in the map.
- First posted on arXiv 27 May 2021.

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Visual Search at Alibaba](https://mlsanity.com/paper/2102.04674/) (2021)
- [Variational Deep Semantic Hashing for Text Documents](https://mlsanity.com/paper/1708.03436/) (2017)
- [NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing](https://mlsanity.com/paper/1805.05361/) (2018)
- [Learning Discrete Structured Representations by Adversarially Maximizing Mutual Information](https://mlsanity.com/paper/2004.03991/) (2020)
- [Unsupervised Semantic Hashing with Pairwise Reconstruction](https://mlsanity.com/paper/2007.00380/) (2020)
- [Correlated Variational Auto-Encoders](https://mlsanity.com/paper/1905.05335/) (2019)
- [Unsupervised Neural Generative Semantic Hashing](https://mlsanity.com/paper/1906.00671/) (2019)
- [Document Hashing with Mixture-Prior Generative Models](https://mlsanity.com/paper/1908.11078/) (2019)
- [Generative Semantic Hashing Enhanced via Boltzmann Machines](https://mlsanity.com/paper/2006.08858/) (2020)

## Abstract (arXiv)

With the need of fast retrieval speed and small memory footprint, document hashing has been playing a crucial role in large-scale information retrieval. To generate high-quality hashing code, both semantics and neighborhood information are crucial. However, most existing methods leverage only one of them or simply combine them via some intuitive criteria, lacking a theoretical principle to guide the integration process. In this paper, we encode the neighborhood information with a graph-induced Gaussian distribution, and propose to integrate the two types of information with a graph-driven generative model. To deal with the complicated correlations among documents, we further propose a tree-structured approximation method for learning. Under the approximation, we prove that the training objective can be decomposed into terms involving only singleton or pairwise documents, enabling the model to be trained as efficiently as uncorrelated ones. Extensive experimental results on three benchmark datasets show that our method achieves superior performance over state-of-the-art methods, demonstrating the effectiveness of the proposed model for simultaneously preserving semantic and neighborhood information.