Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator

Abstract

Semantic hashing has become a crucial component of fast similarity search in many large-scale information retrieval systems, in particular, for text data. Variational auto-encoders (VAEs) with binary latent variables as hashing codes provide state-of-the-art performance in terms of precision for document retrieval. We propose a pairwise loss function with discrete latent VAE to reward within-class similarity and between-class dissimilarity for supervised hashing. Instead of solving the optimization relying on existing biased gradient estimators, an unbiased low-variance gradient estimator is adopted to optimize the hashing function by evaluating the non-differentiable loss function over two correlated sets of binary hashing codes to control the variance of gradient estimates. This new semantic hashing framework achieves superior performance compared to the state-of-the-arts, as demonstrated by our comprehensive experiments.

To appear in UAI 2020

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Categorical Reparameterization with Gumbel-Softmax
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• InfoVAE: Information Maximizing Variational Autoencoders
• Learnable Bernoulli Dropout for Bayesian Deep Learning

Cited by in corpus (3)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Bayesian Graph Neural Networks with Adaptive Connection Sampling
• Self-Supervised Bernoulli Autoencoders for Semi-Supervised Hashing