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

@article{Shen2018NASHTE,
  title={NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing},
  author={Dinghan Shen and Qinliang Su and Paidamoyo Chapfuwa and W. Wang and Guoyin Wang and L. Carin and Ricardo Henao},
  journal={ArXiv},
  year={2018},
  volume={abs/1805.05361}
}
  • Dinghan Shen, Qinliang Su, +4 authors Ricardo Henao
  • Published 2018
  • Computer Science
  • 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… CONTINUE READING
    34 Citations
    Unsupervised Neural Generative Semantic Hashing
    • 10
    • Highly Influenced
    • PDF
    Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator
    • 9
    • Highly Influenced
    • PDF
    Unsupervised Few-Bits Semantic Hashing with Implicit Topics Modeling
    • Highly Influenced
    • PDF
    Document Hashing with Mixture-Prior Generative Models
    • 5
    • PDF
    Discrete Wasserstein Autoencoders for Document Retrieval
    • Y. Zhang, Hao Zhu
    • Computer Science
    • ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2020
    • Highly Influenced
    Unsupervised Semantic Hashing with Pairwise Reconstruction
    • 3
    • Highly Influenced
    • PDF
    Generative Semantic Hashing Enhanced via Boltzmann Machines
    • PDF
    Efficient Implicit Unsupervised Text Hashing using Adversarial Autoencoder
    • 1
    • Highly Influenced
    • PDF
    Learning to Hash with Graph Neural Networks for Recommender Systems
    • 7
    • PDF

    References

    SHOWING 1-10 OF 53 REFERENCES
    Stochastic Generative Hashing
    • 44
    • Highly Influential
    • PDF
    Variational Deep Semantic Hashing for Text Documents
    • 45
    • Highly Influential
    • PDF
    Convolutional Neural Networks for Text Hashing
    • 23
    • Highly Influential
    • PDF
    Deep Supervised Discrete Hashing
    • 130
    • PDF
    Supervised hashing with kernels
    • 1,156
    • PDF
    Semantic hashing
    • 1,150
    • PDF
    Self-taught hashing for fast similarity search
    • 347
    • Highly Influential
    • PDF
    Semi-Supervised Hashing for Large-Scale Search
    • J. Wang, S. Kumar, S. Chang
    • Computer Science, Medicine
    • IEEE Transactions on Pattern Analysis and Machine Intelligence
    • 2012
    • 647
    • PDF
    Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms
    • 169
    • PDF
    Skip-Thought Vectors
    • 1,630
    • PDF