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

By Dinghan Shen, Qinliang Su, Paidamoyo Chapfuwa, Wenlin Wang, Guoyin Wang, Lawrence Carin, Ricardo Henao. 2018

64 citations recorded by the source corpus.

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 backpropagated through the discrete latent variable to optimize the hash function. We also draw the connections between proposed method and rate-distortion theory, which provides a theoretical foundation for the effectiveness of our 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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Retrieval & Search, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Lawrence Carin
2. Dinghan Shen
3. Ricardo Henao
4. Xinyuan Zhang
5. Martin Renqiang Min
6. Tamir Hazan
7. Chunyuan Li
8. Yitong Li

In Computer Vision and Pattern Recognition

1. Lawrence Carin
2. Ricardo Henao
3. Dinghan Shen
4. Martin Renqiang Min
5. Tamir Hazan
6. Xinyuan Zhang
7. Yitong Li
8. Andreea Gane

In Information Retrieval & Search

1. Lawrence Carin
2. Dinghan Shen
3. Yitong Li
4. Martin Renqiang Min
5. Andreea Gane
6. Tommi S. Jaakkola

In Representation & Self-Supervised Learning

1. Dinghan Shen
2. Lawrence Carin
3. Ricardo Henao
4. Tamir Hazan
5. Xinyuan Zhang
6. Yitong Li
7. Martin Renqiang Min
8. Andreea Gane

Citations in the corpus

• Learning Context-Sensitive Convolutional Filters for Text Processing (2017, methodology): “Learning deep text representations has attracted much attention recently, since they can potentially benefit a wide range of NLP applications (Collobert et al., 2011; Kim, 2014; Wang et al., 2017a; Shen et al., 2018a; Tang and de Sa, 2018; Zhang et al., 2018).”
• Improved Semantic-Aware Network Embedding with Fine-Grained Word Alignment (2018, methodology): “We experiment with three variants for our WANE model: ( i ) WANE: where the word embeddings of each text sequence are simply average to obtain the sentence representations, similar to (Joulin et al., 2016; Shen et al., 2018c).”
• Direct Optimization through arg max for Discrete Variational Auto-Encoder (2019, background): “Models with discrete latent variables drive extensive research in machine learning applications, including language classification and generation [39, 9, 31], molecular synthesis [16], or game solving [22].”