As a general-purpose generative model architecture, VAE has been widely used in the field of image and natural language processing. VAE maps high dimensional sample data into continuous latent variables with unsupervised learning. Sampling in the latent variable space of the feature, VAE can construct new image or text data. As a general-purpose generation model, the vanilla VAE can not fit well with various data sets and neural networks with different structures. Because of the need to balance the accuracy of reconstruction and the convenience of latent variable sampling in the training process, VAE often has problems known as "posterior collapse". images reconstructed by VAE are also often blurred. In this paper, we analyze the main cause of these problem, which is the lack of mutual information between the sample variable and the latent feature variable during the training process. To maintain mutual information in model training, we propose to use the auxiliary softmax multi-classification network structure to improve the training effect of VAE, named VAE-AS. We use MNIST and Omniglot data sets to test the VAE-AS model. Based on the test results, It can be show that VAE-AS has obvious effects on the mutual information adjusting and solving the posterior collapse problem.
University of Electronic Science and Technology of China（电子科技大学）；University of Science and Technology of China（中国科学技术大学）；Huawei Cloud Computing Technologies Co., Ltd.（华为云计算技术有限公司）
Variational AutoEncoder (VAE) has been extended as a representative nonlinear method for collaborative filtering. However, the bottleneck of VAE lies in the softmax computation over all items, such that it takes linear costs in the number of items to compute the loss and gradient for optimization. This hinders the practical use due to millions of items in real-world scenarios. Importance sampling is an effective approximation method, based on which the sampled softmax has been derived. However, existing methods usually exploit the uniform or popularity sampler as proposal distributions, leadin…
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. …
Many applications of generative models rely on the marginalization of their high-dimensional output probability distributions. Normalization functions that yield sparse probability distributions can make exact marginalization more computationally tractable. However, sparse normalization functions usually require alternative loss functions for training since the log-likelihood is undefined for sparse probability distributions. Furthermore, many sparse normalization functions often collapse the multimodality of distributions. In this work, we present $\textit{ev-softmax}$, a sparse normalization…
Discrete and especially binary random variables occur in many machine learning models, notably in variational autoencoders with binary latent states and in stochastic binary networks. When learning such models, a key tool is an estimator of the gradient of the expected loss with respect to the probabilities of binary variables. The straight-through (ST) estimator gained popularity due to its simplicity and efficiency, in particular in deep networks where unbiased estimators are impractical. Several techniques were proposed to improve over ST while keeping the same low computational complexity:…
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 $\arg \max$…
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…
Department of Chemical and Biomolecular Engineering, University of Maryland（马里兰大学化学与生物分子工程系）
Conformational sampling of biomolecules using molecular dynamics simulations often produces large amount of high dimensional data that makes it difficult to interpret using conventional analysis techniques. Dimensionality reduction methods are thus required to extract useful and relevant information. Here we devise a machine learning method, Gaussian mixture variational autoencoder (GMVAE) that can simultaneously perform dimensionality reduction and clustering of biomolecular conformations in an unsupervised way. We show that GMVAE can learn a reduced representation of the free energy landscap…
University of Maryland Baltimore County（马里兰大学巴尔的摩县分校）
Within the context of event modeling and understanding, we propose a new method for neural sequence modeling that takes partially-observed sequences of discrete, external knowledge into account. We construct a sequential neural variational autoencoder, which uses Gumbel-Softmax reparametrization within a carefully defined encoder, to allow for successful backpropagation during training. The core idea is to allow semi-supervised external discrete knowledge to guide, but not restrict, the variational latent parameters during training. Our experiments indicate that our approach not only outperfor…
Seoul National University（首尔大学）；Massachusetts Institute of Technology（麻省理工学院）
Incremental class learning, a scenario in continual learning context where classes and their training data are sequentially and disjointedly observed, challenges a problem widely known as catastrophic forgetting. In this work, we propose a novel incremental class learning method that can significantly reduce memory overhead compared to previous approaches. Apart from conventional classification scheme using softmax, our model bases on an autoencoder to extract prototypes for given inputs so that no change in its output unit is required. It stores only the mean of prototypes per class to perfor…
Shahjalal University of Science & Technology（沙赫贾拉尔科技大学）；North East University Bangladesh（孟加拉国东北大学）
This work attempts to find the most optimal parameter setting of a deep artificial neural network (ANN) for Bengali digit dataset by pre-training it using stacked denoising autoencoder (SDA). Although SDA based recognition is hugely popular in image, speech and language processing related tasks among the researchers, it was never tried in Bengali dataset recognition. For this work, a dataset of 70000 handwritten samples were used from (Chowdhury and Rahman, 2016) and was recognized using several settings of network architecture. Among all these settings, the most optimal setting being found to…
Columbia University（哥伦比亚大学）；Peking University（北京大学）
Paraphrase generation is a longstanding important problem in natural language processing. In addition, recent progress in deep generative models has shown promising results on discrete latent variables for text generation. Inspired by variational autoencoders with discrete latent structures, in this work, we propose a latent bag of words (BOW) model for paraphrase generation. We ground the semantics of a discrete latent variable by the BOW from the target sentences. We use this latent variable to build a fully differentiable content planning and surface realization model. Specifically, we use …
A hitchhiker's guide to Poisson gradient estimation
Georgia Institute of Technology（佐治亚理工学院）；Reality Labs, Meta（Meta现实实验室）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院航空信息研究所）；Redwood Center for Theoretical Neuroscience, UC Berkeley（伯克利大学理论神经科学中心）；VERSES AI Research Lab, Los Angeles, USA（洛杉矶VERSES AI研究实验室）
Ambiguity is inevitable in medical images, which often results in different image interpretations (e.g. object boundaries or segmentation maps) from different human experts. Thus, a model that learns the ambiguity and outputs a probability distribution of the target, would be valuable for medical applications to assess the uncertainty of diagnosis. In this paper, we propose a powerful generative model to learn a representation of ambiguity and to generate probabilistic outputs. Our model, named Coordinate Quantization Variational Autoencoder (CQ-VAE) employs a discrete latent space with an int…
University of Science and Technology of China（中国科学技术大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）
Single-step retrosynthesis is the cornerstone of retrosynthesis planning, which is a crucial task for computer-aided drug discovery. The goal of single-step retrosynthesis is to identify the possible reactants that lead to the synthesis of the target product in one reaction. By representing organic molecules as canonical strings, existing sequence-based retrosynthetic methods treat the product-to-reactant retrosynthesis as a sequence-to-sequence translation problem. However, most of them struggle to identify diverse chemical reactions for a desired product due to the deterministic inference, w…
