Variational autoencoders have been widely applied for natural language generation, however, there are two long-standing problems: information under-representation and posterior collapse. The former arises from the fact that only the last hidden state from the encoder is transformed to the latent space, which is insufficient to summarize data. The latter comes as a result of the imbalanced scale between the reconstruction loss and the KL divergence in the objective function. To tackle these issues, in this paper we propose the discrete variational attention model with categorical distribution over the attention mechanism owing to the discrete nature in languages. Our approach is combined with an auto-regressive prior to capture the sequential dependency from observations, which can enhance the latent space for language generation. Moreover, thanks to the property of discreteness, the training of our proposed approach does not suffer from posterior collapse. Furthermore, we carefully analyze the superiority of discrete latent space over the continuous space with the common Gaussian distribution. Extensive experiments on language generation demonstrate superior advantages of our proposed approach in comparison with the state-of-the-art counterparts.
In this thesis, we explore the use of deep neural networks for generation of natural language. Specifically, we implement two sequence-to-sequence neural variational models - variational autoencoders (VAE) and variational encoder-decoders (VED). VAEs for text generation are difficult to train due to issues associated with the Kullback-Leibler (KL) divergence term of the loss function vanishing to zero. We successfully train VAEs by implementing optimization heuristics such as KL weight annealing and word dropout. We also demonstrate the effectiveness of this continuous latent space through exp…
Harvard University（哈佛大学）；School of Engineering and Applied Sciences（工程与应用科学学院）
Neural attention has become central to many state-of-the-art models in natural language processing and related domains. Attention networks are an easy-to-train and effective method for softly simulating alignment; however, the approach does not marginalize over latent alignments in a probabilistic sense. This property makes it difficult to compare attention to other alignment approaches, to compose it with probabilistic models, and to perform posterior inference conditioned on observed data. A related latent approach, hard attention, fixes these issues, but is generally harder to train and les…
Particle-based variational inference offers a flexible way of approximating complex posterior distributions with a set of particles. In this paper we introduce a new particle-based variational inference method based on the theory of semi-discrete optimal transport. Instead of minimizing the KL divergence between the posterior and the variational approximation, we minimize a semi-discrete optimal transport divergence. The solution of the resulting optimal transport problem provides both a particle approximation and a set of optimal transportation densities that map each particle to a segment of…
University at Buffalo（布法罗大学）；Criteo（Criteo公司）；Duke University（杜克大学）
Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. However, the sequential text generation common pitfall with VAEs is that the model tends to ignore latent variables with a strong auto-regressive decoder. In this paper, we propose a principled approach to alleviate this issue by applying a discretized bottleneck to enforce an implicit latent feature matching in a more compact latent space. We impose a shared discrete latent space where each input is learned to choose a combination of latent atoms as a regularized latent representation. Our model endows …
Training of discrete latent variable models remains challenging because passing gradient information through discrete units is difficult. We propose a new class of smoothing transformations based on a mixture of two overlapping distributions, and show that the proposed transformation can be used for training binary latent models with either directed or undirected priors. We derive a new variational bound to efficiently train with Boltzmann machine priors. Using this bound, we develop DVAE++, a generative model with a global discrete prior and a hierarchy of convolutional continuous variables. …
Reparameterization of variational auto-encoders with continuous random variables is an effective method for reducing the variance of their gradient estimates. In the discrete case, one can perform reparametrization using the Gumbel-Max trick, but the resulting objective relies on an $\arg \max$ operation and is non-differentiable. In contrast to previous works which resort to softmax-based relaxations, we propose to optimize it directly by applying the direct loss minimization approach. Our proposal extends naturally to structured discrete latent variable models when evaluating the $\arg \max$…
Probabilistic models with discrete latent variables naturally capture datasets composed of discrete classes. However, they are difficult to train efficiently, since backpropagation through discrete variables is generally not possible. We present a novel method to train a class of probabilistic models with discrete latent variables using the variational autoencoder framework, including backpropagation through the discrete latent variables. The associated class of probabilistic models comprises an undirected discrete component and a directed hierarchical continuous component. The discrete compon…
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；The Chinese University of Hong Kong（香港中文大学）
Variational autoencoders (VAEs) have been widely applied for text modeling. In practice, however, they are troubled by two challenges: information underrepresentation and posterior collapse. The former arises as only the last hidden state of LSTM encoder is transformed into the latent space, which is generally insufficient to summarize the data. The latter is a long-standing problem during the training of VAEs as the optimization is trapped to a disastrous local optimum. In this paper, we propose Discrete Auto-regressive Variational Attention Model (DAVAM) to address the challenges. Specifical…
Helsinki Institute for Information Technology HIIT（赫尔辛基信息技术研究所（HIIT））；University of Helsinki（赫尔辛基大学）
Variational approximations are increasingly based on gradient-based optimization of expectations estimated by sampling. Handling discrete latent variables is then challenging because the sampling process is not differentiable. Continuous relaxations, such as the Gumbel-Softmax for categorical distribution, enable gradient-based optimization, but do not define a valid probability mass for discrete observations. In practice, selecting the amount of relaxation is difficult and one needs to optimize an objective that does not align with the desired one, causing problems especially with models havi…
Boltzmann machines are powerful distributions that have been shown to be an effective prior over binary latent variables in variational autoencoders (VAEs). However, previous methods for training discrete VAEs have used the evidence lower bound and not the tighter importance-weighted bound. We propose two approaches for relaxing Boltzmann machines to continuous distributions that permit training with importance-weighted bounds. These relaxations are based on generalized overlapping transformations and the Gaussian integral trick. Experiments on the MNIST and OMNIGLOT datasets show that these r…
We propose a VAE for Transformers by developing a variational information bottleneck regulariser for Transformer embeddings. We formalise the embedding space of Transformer encoders as mixture probability distributions, and use Bayesian nonparametrics to derive a nonparametric variational information bottleneck (NVIB) for such attention-based embeddings. The variable number of mixture components supported by nonparametric methods captures the variable number of vectors supported by attention, and the exchangeability of our nonparametric distributions captures the permutation invariance of atte…
We show how to use a variational approximation to the logistic function to perform approximate inference in Bayesian networks containing discrete nodes with continuous parents. Essentially, we convert the logistic function to a Gaussian, which facilitates exact inference, and then iteratively adjust the variational parameters to improve the quality of the approximation. We demonstrate experimentally that this approximation is faster and potentially more accurate than sampling. We also introduce a simple new technique for handling evidence, which allows us to handle arbitrary distributions on o…
University of British Columbia（不列颠哥伦比亚大学）；MIT（麻省理工学院）
We introduce the thermodynamic variational objective (TVO) for learning in both continuous and discrete deep generative models. The TVO arises from a key connection between variational inference and thermodynamic integration that results in a tighter lower bound to the log marginal likelihood than the standard variational variational evidence lower bound (ELBO) while remaining as broadly applicable. We provide a computationally efficient gradient estimator for the TVO that applies to continuous, discrete, and non-reparameterizable distributions and show that the objective functions used in var…
Monash University（莫纳什大学）；Indian Institute of Technology, Kanpur（印度理工学院坎普尔分校）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Many applications, such as text modelling, high-throughput sequencing, and recommender systems, require analysing sparse, high-dimensional, and overdispersed discrete (count-valued or binary) data. Although probabilistic matrix factorisation and linear/nonlinear latent factor models have enjoyed great success in modelling such data, many existing models may have inferior modelling performance due to the insufficient capability of modelling overdispersion in count-valued data and model misspecification in general. In this paper, we comprehensively study these issues and propose a variational au…
Technion, IIT（以色列理工学院）；Meta AI Research（Meta人工智能研究院）
Discrete variational auto-encoders (VAEs) are able to represent semantic latent spaces in generative learning. In many real-life settings, the discrete latent space consists of high-dimensional structures, and propagating gradients through the relevant structures often requires enumerating over an exponentially large latent space. Recently, various approaches were devised to propagate approximated gradients without enumerating over the space of possible structures. In this work, we use Natural Evolution Strategies (NES), a class of gradient-free black-box optimization algorithms, to learn disc…
University of Maryland Baltimore County（马里兰大学巴尔的摩县分校）
We show how to learn a neural topic model with discrete random variables---one that explicitly models each word's assigned topic---using neural variational inference that does not rely on stochastic backpropagation to handle the discrete variables. The model we utilize combines the expressive power of neural methods for representing sequences of text with the topic model's ability to capture global, thematic coherence. Using neural variational inference, we show improved perplexity and document understanding across multiple corpora. We examine the effect of prior parameters both on the model a…
Insilico Medicine（英矽智能）；National Research University Higher School of Economics（国立研究型高等经济大学）
Variational autoencoders are prominent generative models for modeling discrete data. However, with flexible decoders, they tend to ignore the latent codes. In this paper, we study a VAE model with a deterministic decoder (DD-VAE) for sequential data that selects the highest-scoring tokens instead of sampling. Deterministic decoding solely relies on latent codes as the only way to produce diverse objects, which improves the structure of the learned manifold. To implement DD-VAE, we propose a new class of bounded support proposal distributions and derive Kullback-Leibler divergence for Gaussian …
University of Cambridge（剑桥大学）；HHMI Janelia Research Campus（HHMI珍妮亚研究园区）
Each training step for a variational autoencoder (VAE) requires us to sample from the approximate posterior, so we usually choose simple (e.g. factorised) approximate posteriors in which sampling is an efficient computation that fully exploits GPU parallelism. However, such simple approximate posteriors are often insufficient, as they eliminate statistical dependencies in the posterior. While it is possible to use normalizing flow approximate posteriors for continuous latents, some problems have discrete latents and strong statistical dependencies. The most natural approach to model these depe…
Discrete latent variables are considered important for real world data, which has motivated research on Variational Autoencoders (VAEs) with discrete latents. However, standard VAE training is not possible in this case, which has motivated different strategies to manipulate discrete distributions in order to train discrete VAEs similarly to conventional ones. Here we ask if it is also possible to keep the discrete nature of the latents fully intact by applying a direct discrete optimization for the encoding model. The approach is consequently strongly diverting from standard VAE-training by si…
Gradient-based approximate inference methods, such as Stein variational gradient descent (SVGD), provide simple and general-purpose inference engines for differentiable continuous distributions. However, existing forms of SVGD cannot be directly applied to discrete distributions. In this work, we fill this gap by proposing a simple yet general framework that transforms discrete distributions to equivalent piecewise continuous distributions, on which the gradient-free SVGD is applied to perform efficient approximate inference. The empirical results show that our method outperforms traditional a…
Khoury College of Computer Sciences, Northeastern University（东北大学Khoury计算机科学学院）
Abstraction is crucial for effective sequential decision making in domains with large state spaces. In this work, we propose an information bottleneck method for learning approximate bisimulations, a type of state abstraction. We use a deep neural encoder to map states onto continuous embeddings. We map these embeddings onto a discrete representation using an action-conditioned hidden Markov model, which is trained end-to-end with the neural network. Our method is suited for environments with high-dimensional states and learns from a stream of experience collected by an agent acting in a Marko…
Calorimeter simulation is the most computationally expensive part of Monte Carlo generation of samples necessary for analysis of experimental data at the Large Hadron Collider (LHC). The High-Luminosity upgrade of the LHC would require an even larger amount of such samples. We present a technique based on Discrete Variational Autoencoders (DVAEs) to simulate particle showers in Electromagnetic Calorimeters. We discuss how this work paves the way towards exploration of quantum annealing processors as sampling devices for generation of simulated High Energy Physics datasets.
Improved Variational Inference in Discrete VAEs using Error Correcting Codes
Dept. of Signal Theory and Communications, Universidad Rey Juan Carlos（信号理论与通信系，雷乌安卡洛斯大学）；Klipsch School of Electrical and Computer Engineering, New Mexico State University（电气与计算机工程学院，新墨西哥州立大学）；Instituto de Investigación Sanitaria Gregorio Marañón, Madrid, Spain（格里戈里奥·马兰农卫生研究所，马德里，西班牙）
Variational Autoencoder is a scalable method for learning latent variable models of complex data. It employs a clear objective that can be easily optimized. However, it does not explicitly measure the quality of learned representations. We propose a Variational Mutual Information Maximization Framework for VAE to address this issue. It provides an objective that maximizes the mutual information between latent codes and observations. The objective acts as a regularizer that forces VAE to not ignore the latent code and allows one to select particular components of it to be most informative with …
Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling
School of Mathematical Sciences, Peking University（北京大学数学科学学院）；Center for Statistical Science, Peking University（北京大学统计科学中心）；Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）；Huawei Foundation Model Dept（华为基金会模型部门）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
There has recently been significant interest in hard attention models for tasks such as object recognition, visual captioning and speech recognition. Hard attention can offer benefits over soft attention such as decreased computational cost, but training hard attention models can be difficult because of the discrete latent variables they introduce. Previous work used REINFORCE and Q-learning to approach these issues, but those methods can provide high-variance gradient estimates and be slow to train. In this paper, we tackle the problem of learning hard attention for a sequential task using va…
Topic models have been widely explored as probabilistic generative models of documents. Traditional inference methods have sought closed-form derivations for updating the models, however as the expressiveness of these models grows, so does the difficulty of performing fast and accurate inference over their parameters. This paper presents alternative neural approaches to topic modelling by providing parameterisable distributions over topics which permit training by backpropagation in the framework of neural variational inference. In addition, with the help of a stick-breaking construction, we p…
The University of Tokyo（东京大学）；Keio University（庆应义塾大学）；IBM Japan（IBM日本）
Quantum classifiers provide sophisticated embeddings of input data in Hilbert space promising quantum advantage. The advantage stems from quantum feature maps encoding the inputs into quantum states with variational quantum circuits. A recent work shows how to map discrete features with fewer quantum bits using Quantum Random Access Coding (QRAC), an important primitive to encode binary strings into quantum states. We propose a new method to embed discrete features with trainable quantum circuits by combining QRAC and a recently proposed strategy for training quantum feature map called quantum…
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）
Recently, the speaker clustering model based on aggregation hierarchy cluster (AHC) is a common method to solve two main problems: no preset category number clustering and fix category number clustering. In general, model takes features like i-vectors as input of probability and linear discriminant analysis model (PLDA) aims to form the distance matric in long voice application scenario, and then clustering results are obtained through the clustering model. However, traditional speaker clustering method based on AHC has the shortcomings of long-time running and remains sensitive to environment…
Korea Advanced Institute of Science and Technology（韩国科学技术院）
Learning interpretable and disentangled representations of data is a key topic in machine learning research. Variational Autoencoder (VAE) is a scalable method for learning directed latent variable models of complex data. It employs a clear and interpretable objective that can be easily optimized. However, this objective does not provide an explicit measure for the quality of latent variable representations which may result in their poor quality. We propose Variational Mutual Information Maximization Framework for VAE to address this issue. In comparison to other methods, it provides an explic…
Variational Quantum Attention for Molecular Graph Learning
National Yang Ming Chiao Tung University（国立阳明交通大学）；Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Brookhaven National Laboratory（布鲁克海文国家实验室）；Taipei Medical University（台北医学大学）
Sony Group Corporation（索尼集团公司）；Sony Corporation of America（美国索尼公司）
One noted issue of vector-quantized variational autoencoder (VQ-VAE) is that the learned discrete representation uses only a fraction of the full capacity of the codebook, also known as codebook collapse. We hypothesize that the training scheme of VQ-VAE, which involves some carefully designed heuristics, underlies this issue. In this paper, we propose a new training scheme that extends the standard VAE via novel stochastic dequantization and quantization, called stochastically quantized variational autoencoder (SQ-VAE). In SQ-VAE, we observe a trend that the quantization is stochastic at the …
Inference in discrete graphical models with variational methods is difficult because of the inability to re-parameterize gradients of the Evidence Lower Bound (ELBO). Many sampling-based methods have been proposed for estimating these gradients, but they suffer from high bias or variance. In this paper, we propose a new approach that leverages the tractability of probabilistic circuit models, such as Sum Product Networks (SPN), to compute ELBO gradients exactly (without sampling) for a certain class of densities. In particular, we show that selective-SPNs are suitable as an expressive variatio…
Data Science Institute, Imperial College London（伦敦帝国理工学院数据科学研究所）；Universidad de Granada（格拉纳达大学）
We propose a new 'Bi-Reduced Space' approach to solving 3D Variational Data Assimilation using Convolutional Autoencoders. We prove that our approach has the same solution as previous methods but has significantly lower computational complexity; in other words, we reduce the computational cost without affecting the data assimilation accuracy. We tested the new method with data from a real-world application: a pollution model of a site in Elephant and Castle, London and found that we could reduce the size of the background covariance matrix representation by O(10^3) and, at the same time, incre…
Automatic MRI brain tumor segmentation is of vital importance for the disease diagnosis, monitoring, and treatment planning. In this paper, we propose a two-stage encoder-decoder based model for brain tumor subregional segmentation. Variational autoencoder regularization is utilized in both stages to prevent the overfitting issue. The second-stage network adopts attention gates and is trained additionally using an expanded dataset formed by the first-stage outputs. On the BraTS 2020 validation dataset, the proposed method achieves the mean Dice score of 0.9041, 0.8350, and 0.7958, and Hausdorf…
University Sapienza（罗马第一大学）；National Research Council (ISC-CNR)（国家研究委员会（复杂系统研究所））；Research Center Enrico Fermi (CREF)（恩里科·费米研究中心）
In the context of quantum information, highly nonlinear regimes, such as those supporting solitons, are marginally investigated. We miss general methods for quantum solitons, although they can act as entanglement generators or as self-organized quantum processors. We develop a computational approach that uses a neural network as a variational ansatz for quantum solitons in an array of waveguides. By training the resulting phase-space quantum machine learning model, we find different soliton solutions varying the number of particles and interaction strength. We consider Gaussian states that ena…
Discrete latent spaces in variational autoencoders have been shown to effectively capture the data distribution for many real-world problems such as natural language understanding, human intent prediction, and visual scene representation. However, discrete latent spaces need to be sufficiently large to capture the complexities of real-world data, rendering downstream tasks computationally challenging. For instance, performing motion planning in a high-dimensional latent representation of the environment could be intractable. We consider the problem of sparsifying the discrete latent space of a…
