Semantic hashing is an emerging technique for large-scale similarity search based on representing high-dimensional data using similarity-preserving binary codes used for efficient indexing and search. It has recently been shown that variational autoencoders, with Bernoulli latent representations parametrized by neural nets, can be successfully trained to learn such codes in supervised and unsupervised scenarios, improving on more traditional methods thanks to their ability to handle the binary constraints architecturally. However, the scenario where labels are scarce has not been studied yet.
This paper investigates the robustness of hashing methods based on variational autoencoders to the lack of supervision, focusing on two semi-supervised approaches currently in use. The first augments the variational autoencoder's training objective to jointly model the distribution over the data and the class labels. The second approach exploits the annotations to define an additional pairwise loss that enforces consistency between the similarity in the code (Hamming) space and the similarity in the label space. Our experiments show that both methods can significantly increase the hash codes' quality. The pairwise approach can exhibit an advantage when the number of labelled points is large. However, we found that this method degrades quickly and loses its advantage when labelled samples decrease. To circumvent this problem, we propose a novel supervision method in which the model uses its label distribution predictions to implement the pairwise objective. Compared to the best baseline, this procedure yields similar performance in fully supervised settings but improves the results significantly when labelled data is scarce. Our code is made publicly available at https://github.com/amacaluso/SSB-VAE.
Texas A&M University（德州农工大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
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 a…
Variational autoencoders (VAE) have quickly become a central tool in machine learning, applicable to a broad range of data types and latent variable models. By far the most common first step, taken by seminal papers and by core software libraries alike, is to model MNIST data using a deep network parameterizing a Bernoulli likelihood. This practice contains what appears to be and what is often set aside as a minor inconvenience: the pixel data is [0,1] valued, not {0,1} as supported by the Bernoulli likelihood. Here we show that, far from being a triviality or nuisance that is convenient to ig…
Fraunhofer ITWM（弗劳恩霍夫工业数学研究所）；Technical University of Kaiserslautern（凯泽斯劳滕工业大学）
We consider a variational autoencoder (VAE) for binary data. Our main innovations are an interpretable lower bound for its training objective, a modified initialization and architecture of such a VAE that leads to faster training, and a decision support for finding the appropriate dimension of the latent space via using a PCA. Numerical examples illustrate our theoretical result and the performance of the new architecture.
Fast similarity search is a key component in large-scale information retrieval, where semantic hashing has become a popular strategy for representing documents as binary hash codes. Recent advances in this area have been obtained through neural network based models: generative models trained by learning to reconstruct the original documents. We present a novel unsupervised generative semantic hashing approach, \textit{Ranking based Semantic Hashing} (RBSH) that consists of both a variational and a ranking based component. Similarly to variational autoencoders, the variational component is trai…
Duke University（杜克大学）；University of Minnesota-Twin Cities（明尼苏达大学双城分校）
Motivated by the ever-increasing demands for limited communication bandwidth and low-power consumption, we propose a new methodology, named joint Variational Autoencoders with Bernoulli mixture models (VAB), for performing clustering in the compressed data domain. The idea is to reduce the data dimension by Variational Autoencoders (VAEs) and group data representations by Bernoulli mixture models (BMMs). Once jointly trained for compression and clustering, the model can be decomposed into two parts: a data vendor that encodes the raw data into compressed data, and a data consumer that classifi…
Distributions are fundamental statistical elements that play essential theoretical and practical roles. The article discusses experiences of training neural networks to classify univariate empirical distributions and to represent them on the two-dimensional latent space forcing disentanglement based on the inputs of cumulative distribution functions (CDF). The latent space representation has been performed using an unsupervised beta variational autoencoder (beta-VAE). It separates distributions of different shapes while overlapping similar ones and empirically realises relationships between di…
This paper will explore the use of autoencoders for semantic hashing in the context of Information Retrieval. This paper will summarize how to efficiently train an autoencoder in order to create meaningful and low-dimensional encodings of data. This paper will demonstrate how computing and storing the closest encodings to an input query can help speed up search time and improve the quality of our search results. The novel contributions of this paper involve using the representation of the data learned by an auto-encoder in order to augment our search query in various ways. I present and evalua…
After an autoencoder (AE) has learnt to reconstruct one dataset, it might be expected that the likelihood on an out-of-distribution (OOD) input would be low. This has been studied as an approach to detect OOD inputs. Recent work showed this intuitive approach can fail for the dataset pairs FashionMNIST vs MNIST. This paper suggests this is due to the use of Bernoulli likelihood and analyses why this is the case, proposing two fixes: 1) Compute the uncertainty of likelihood estimate by using a Bayesian version of the AE. 2) Use alternative distributions to model the likelihood.
An attractive approach for fast search in image databases is binary hashing, where each high-dimensional, real-valued image is mapped onto a low-dimensional, binary vector and the search is done in this binary space. Finding the optimal hash function is difficult because it involves binary constraints, and most approaches approximate the optimization by relaxing the constraints and then binarizing the result. Here, we focus on the binary autoencoder model, which seeks to reconstruct an image from the binary code produced by the hash function. We show that the optimization can be simplified wit…
Spiking neural networks (SNNs) can be run on neuromorphic devices with ultra-high speed and ultra-low energy consumption because of their binary and event-driven nature. Therefore, SNNs are expected to have various applications, including as generative models being running on edge devices to create high-quality images. In this study, we build a variational autoencoder (VAE) with SNN to enable image generation. VAE is known for its stability among generative models; recently, its quality advanced. In vanilla VAE, the latent space is represented as a normal distribution, and floating-point calcu…
Rutgers University（罗格斯大学）；Toyota Technological Institute at Chicago（芝加哥丰田工业大学）
We propose learning discrete structured representations from unlabeled data by maximizing the mutual information between a structured latent variable and a target variable. Calculating mutual information is intractable in this setting. Our key technical contribution is an adversarial objective that can be used to tractably estimate mutual information assuming only the feasibility of cross entropy calculation. We develop a concrete realization of this general formulation with Markov distributions over binary encodings. We report critical and unexpected findings on practical aspects of the objec…
Indian Institute of Technology Roorkee（印度理工学院鲁基分校）
In this report, we introduce a video hashing method for scalable video segment copy detection. The objective of video segment copy detection is to find the video (s) present in a large database, one of whose segments (cropped in time) is a (transformed) copy of the given query video. This transformation may be temporal (for example frame dropping, change in frame rate) or spatial (brightness and contrast change, addition of noise etc.) in nature although the primary focus of this report is detecting temporal attacks. The video hashing method proposed by us uses a deep learning neural network t…
Binary concepts are empirically used by humans to generalize efficiently. And they are based on Bernoulli distribution which is the building block of information. These concepts span both low-level and high-level features such as "large vs small" and "a neuron is active or inactive". Binary concepts are ubiquitous features and can be used to transfer knowledge to improve model generalization. We propose a novel binarized regularization to facilitate learning of binary concepts to improve the quality of data generation in autoencoders. We introduce a binarizing hyperparameter $r$ in data genera…
Variational inference is a powerful approach for approximate posterior inference. However, it is sensitive to initialization and can be subject to poor local optima. In this paper, we develop proximity variational inference (PVI). PVI is a new method for optimizing the variational objective that constrains subsequent iterates of the variational parameters to robustify the optimization path. Consequently, PVI is less sensitive to initialization and optimization quirks and finds better local optima. We demonstrate our method on three proximity statistics. We study PVI on a Bernoulli factor model…
Virginia Tech（弗吉尼亚理工大学）；University of Minnesota（明尼苏达大学）；Purdue University（普渡大学）
Image hashing is one of the fundamental problems that demand both efficient and effective solutions for various practical scenarios. Adversarial autoencoders are shown to be able to implicitly learn a robust, locality-preserving hash function that generates balanced and high-quality hash codes. However, the existing adversarial hashing methods are inefficient to be employed for large-scale image retrieval applications. Specifically, they require an exponential number of samples to be able to generate optimal hash codes and a significantly high computational cost to train. In this paper, we sho…
Sun Yat-sen University（中山大学）；Microsoft Dynamics 365 AI（微软Dynamics 365人工智能部门）；SUNY at Buffalo（纽约州立大学布法罗分校）
Generative semantic hashing is a promising technique for large-scale information retrieval thanks to its fast retrieval speed and small memory footprint. For the tractability of training, existing generative-hashing methods mostly assume a factorized form for the posterior distribution, enforcing independence among the bits of hash codes. From the perspectives of both model representation and code space size, independence is always not the best assumption. In this paper, to introduce correlations among the bits of hash codes, we propose to employ the distribution of Boltzmann machine as the va…
Northwestern Polytechnical University（西北工业大学）；University of Oulu（奥卢大学）
Learning based hashing plays a pivotal role in large-scale visual search. However, most existing hashing algorithms tend to learn shallow models that do not seek representative binary codes. In this paper, we propose a novel hashing approach based on unsupervised deep learning to hierarchically transform features into hash codes. Within the heterogeneous deep hashing framework, the autoencoder layers with specific constraints are considered to model the nonlinear mapping between features and binary codes. Then, a Restricted Boltzmann Machine (RBM) layer with constraints is utilized to reduce t…
Southwest Jiaotong University（西南交通大学）；Sichuan University（四川大学）；University of Macau（澳门大学）
The excellent performance of representation learning of autoencoders have attracted considerable interest in various applications. However, the structure and multi-local collaborative relationships of unlabeled data are ignored in their encoding procedure that limits the capability of feature extraction. This paper presents a Multi-local Collaborative AutoEncoder (MC-AE), which consists of novel multi-local collaborative representation RBM (mcrRBM) and multi-local collaborative representation GRBM (mcrGRBM) models. Here, the Locality Sensitive Hashing (LSH) method is used to divide the input d…
Andalusian Research Institute in Data Science and Computational Intelligence（安达卢西亚数据科学与计算智能研究所）；Universidad de Granada（格拉纳达大学）；Universidad de Jaén（哈恩大学）
Autoencoders are techniques for data representation learning based on artificial neural networks. Differently to other feature learning methods which may be focused on finding specific transformations of the feature space, they can be adapted to fulfill many purposes, such as data visualization, denoising, anomaly detection and semantic hashing. This work presents these applications and provides details on how autoencoders can perform them, including code samples making use of an R package with an easy-to-use interface for autoencoder design and training, \texttt{ruta}. Along the way, the expl…
University of Granada（格拉纳达大学）；University of Jaén（哈恩大学）
In many machine learning tasks, learning a good representation of the data can be the key to building a well-performant solution. This is because most learning algorithms operate with the features in order to find models for the data. For instance, classification performance can improve if the data is mapped to a space where classes are easily separated, and regression can be facilitated by finding a manifold of data in the feature space. As a general rule, features are transformed by means of statistical methods such as principal component analysis, or manifold learning techniques such as Iso…
University of Wisconsin（威斯康星大学）；University of Illinois（伊利诺伊大学）；American Family Insurance（美国家庭保险公司）
Transformer-based models are widely used in natural language processing (NLP). Central to the transformer model is the self-attention mechanism, which captures the interactions of token pairs in the input sequences and depends quadratically on the sequence length. Training such models on longer sequences is expensive. In this paper, we show that a Bernoulli sampling attention mechanism based on Locality Sensitive Hashing (LSH), decreases the quadratic complexity of such models to linear. We bypass the quadratic cost by considering self-attention as a sum of individual tokens associated with Be…
