A novel cross-modal auto-encoder associates different data types efficiently.
problem Cross-modal data association in heterogeneous datasets.
method Bayesian inference framework with variational auto-encoders and associators.
result Successfully associates visual and auditory data with minimal paired data.
CVAEs improve VAEs by accounting for correlations in latent representations.
problem VAEs fail to account for correlations between data points, limiting their effectiveness.
method CVAEs incorporate correlation structure into VAEs using a prior and tractable approximations.
result CVAEs outperform baseline algorithms in matching and link prediction tasks.
This paper integrates auto-encoders and GANs using variational inference.
problem Preventing mode collapse in generative models.
method Develops a principle to combine variational auto-encoders and GANs, using synthetic likelihoods and implicit posterior distributions.
result Unified objective for optimizing the fusion of variational auto-encoders and GANs.
SIG-VAE enhances VGAE for graph data modeling.
problem Limited flexibility in VGAE for graph data.
method Hierarchical variational framework with Bernoulli-Poisson link decoder.
result SIG-VAE outperforms state-of-the-art methods on graph tasks.
DGA and DVGA learn disentangled graph representations to improve graph analysis.
problem Holistic graph auto-encoders fail to capture latent factors effectively.
method Design disentangled graph convolutional network and component-wise flow, impose independence constraints.
result Improved disentangled graph representations enhance graph analysis tasks.
Direct optimization of discrete variational auto-encoders using arg max.
problem Optimizing discrete latent variables in variational auto-encoders.
method Direct optimization through arg max without softmax relaxations.
result Empirical effectiveness of direct loss minimization in discrete latent variables.
CasVAE outperforms supervised methods for star-galaxy classification.
problem Challenges in machine learning for astronomy data.
method Cascade Variational Auto-Encoder (CasVAE) for unsupervised star-galaxy classification.
result CasVAE outperforms baseline models in accuracy and stability.
Paper proposes a new method for learning deep generative models using annealed importance sampling.
problem Learning deep generative models efficiently and accurately.
method Proposes annealed importance sampling as a bridge between variational inference and Markov chain Monte Carlo.
result Demonstrates improved density models and better trade-off between computation and model accuracy.
VGAE learns latent representations for graphs using latent variables.
problem Learning interpretable latent representations for undirected graphs.
method Variational auto-encoder framework with graph convolutional network encoder and inner product decoder.
result VGAE achieves competitive link prediction results and improves performance with node features.
Improved reliability of machine learning predictions using variational auto-encoders.
problem Individual unreliability of machine learning models.
method Modified variational auto-encoders to identify a low-dimensional space for reliable classification.
result Improved reliability of predictions and robust identification of adversarial samples.
ACVAEs improve on CVAEs by learning more flexible latent correlations.
problem Learning latent representations with correlated structure.
method Adaptive prior distribution and belief propagation.
result ACVAEs outperform CVAEs in link prediction and hierarchical clustering.
Self-supervised VAEs improve data compression and generation.
problem Efficient data compression and generation.
method Introducing self-supervised Variational Auto-Encoders with deterministic and discrete variational posteriors.
result Self-supervised VAEs simplify the objective function and improve data reconstruction.
A scalable deep generative model using variational auto-encoding and deep Gaussian processes.
problem Deep unsupervised learning and Bayesian optimization challenges.
method Augmenting deep Gaussian processes with a recognition model and variational framework to prevent parameter proliferation.
result Efficacy demonstrated on deep unsupervised learning and Bayesian optimization challenges.
Tighter ELBOs can harm learning, new algorithms improve performance.
problem Theoretical and empirical evidence shows that tighter ELBOs can reduce the signal-to-noise ratio of gradient estimators, hindering learning.
method Introduce three new algorithms: PIWAE, MIWAE, CIWAE, which improve over the standard IWAE.
result New algorithms can deliver improvements over IWAE, even when measured by IWAE's performance.
Spatial VAEs use MVN distributions to encode spatial information explicitly.
problem Capturing spatial information in latent space using traditional VAEs.
method Propose spatial VAEs using matrix-variate normal distributions and low-rank MVN distributions.
result Spatial VAEs outperform traditional VAEs in capturing spatial information.
New method improves Variational Auto-Encoders using convex combination of Inverse Autoregressive Flows.
problem Improving Variational Auto-Encoders (VAEs) for better performance.
method Introducing multiple lower-triangular matrices with ones on the diagonal and combining them using a convex combination to enrich a linear Inverse Autoregressive Flow.
result The proposed method outperforms other volume-preserving flows and is competitive with state-of-the-art linear normalizing flows.
Unbiased gradient estimation improves VAE performance.
problem Training VAEs via maximum likelihood is difficult due to intractable integrals.
method Introduced unbiased estimators of the log-likelihood gradient using coupled Markov chains.
result Unbiased estimators lead to better predictive performance in VAEs.
Paper proposes a fair auto-encoder using hierarchical VampPrior and mutual information.
problem Learning fair representations to remove biases in decision-making.
method Hierarchical Variational Auto-Encoder with mutual information regularization.
result The approach either outperforms or performs on par with the current best model in experiments.
Poincaré VAEs improve hierarchical data representation.
problem Hierarchical data structures are difficult to represent in Euclidean latent spaces.
method Introducing Poincaré ball model of hyperbolic geometry as a latent space for VAEs.
result Better generalization and hierarchical structure recovery in hyperbolic space.
A new triad decoder improves graph auto-encoders' performance.
problem Graph auto-encoders ignore edge interactions, leading to suboptimal predictions.
method Integrates triadic closure property to predict three edges in a local triad.
result Triad decoder leads to more accurate predictions, clustering, and graph characteristics preservation.
AEVB improves understanding of latent variable models.
problem Training latent variable models efficiently and understanding their limitations.
method Motivates AEVB from EM, emphasizing approximate E-step and M-step.
result AEVB tightens ELBO, improving model training.
This paper proposes a method to train energy-based models using variational auto-encoders for efficient sampling.
problem Training energy-based models by maximum likelihood is challenging due to intractable partition functions and difficult sampling from the model distribution.
method The authors propose using a variational auto-encoder to initialize finite-step MCMC sampling, specifically Langevin dynamics, to train the energy-based model.
result The proposed method enables training energy-based models using maximum likelihood, generating samples comparable to GANs and EBMs.
New distribution on simplex for auto-encoding tasks.
problem Developing a new distribution for sparsity in auto-encoding models.
method Using Kumaraswamy distribution and ordered stick-breaking process.
result The new distribution has an exact and closed form reparameterization.
Proposes a method to enforce structural constraints in auto-encoding variational Bayes.
problem Difficulty in imposing structural constraints on approximate posterior of generative models.
method Uses kernel-based measures of independence (dHSIC) to enforce independence between latent representations and nuisance factors.
result Shows superior performance in learning interpretable representations, especially in scRNA-seq.
Anomaly detection method separates contextual from behavioral attributes.
problem Detect anomalies in data without labeled examples.
method Uses joint deep variational generative models.
result Robust to anomalous or novel contextual attributes.
New model learns deep, sparse hierarchies of features from images.
problem Learning deep, sparse hierarchies of features from natural images.
method Structured variational auto-encoder with rectified Gaussian units.
result Joint training of deep models with many layers of latent variables.
The paper evaluates variational auto-encoders using model criticism methods.
problem Evaluating the quality of variational auto-encoders (VAEs).
method Statistical model criticism, focusing on reproducing statistics of unknown data generating processes.
result The proposed framework offers possibilities for model selection beyond intrinsic metrics.
We propose a novel GP auto-encoder for ordinal facial action unit prediction.
problem Simultaneous feature fusion and modeling of discrete ordinal outputs.
method Variational Gaussian Process Auto-Encoder (GPAE) with latent space projection and ordinal label constraints.
result Our model achieves robust feature fusion and joint ordinal prediction of facial action units.
A new tensor decomposition model using variational auto-encoder.
problem Capturing nonlinear relationships in multiway data.
method Bayesian generative model with variational auto-encoder for tensor decomposition.
result Significantly higher prediction performance compared to state-of-the-art methods.
Wasserstein Auto-Encoders minimize Wasserstein distance for better data modeling.
problem Building a generative model of data distributions.
method Minimizes a penalized Wasserstein distance between model and target distributions.
result Generates better quality samples compared to other techniques.
Paper formalizes and analyzes a new bound for variational inference.
problem Lack of theoretical guarantees in variational algorithms.
method Introduces VR-IWAE bound, a generalization of IWAE.
result VR-IWAE bound leads to unbiased gradient estimators.
Paper improves VAEs using Monte Carlo methods.
problem Improving the Evidence Lower Bound (ELBO) for VAEs.
method Uses Monte Carlo techniques to improve ELBO, specifically Sequential Importance Sampling (SIS) with carefully chosen kernels.
result Demonstrates improved performance on various applications.
The paper proposes a new method to train Auto-Encoders using mutual information.
problem Training Auto-Encoders with complex distributions.
method Regularization using mutual information minimization during training, with non-parametric entropy estimation.
result The proposed non-parametric models have better representation learning of complex distributions.
WWAE improves deep generative models by minimizing penalized optimal transport.
problem Challenges in learning deep generative models, such as blurriness in variational auto-encoders and instability in generative adversarial networks.
method WWAE formulates as minimization of penalized optimal transport between target and generated distributions. It uses closed-form squared Wasserstein-2 distance for Gaussians.
result WWAE learns better latent structures and generates higher quality samples than VAEs and GANs.
New anomaly score for generative models without manifold assumptions.
problem Reconstruction error's theoretical limitations for generative models.
method Defining a new anomaly score compatible with generative models.
result The new score is theoretically sound and practical for auto-encoders.
This research tackles automatic paraphrasing without translation.
problem Automatic paraphrasing without translation.
method Proposes a residual variant of vector-quantized variational auto-encoder trained on an unlabeled monolingual corpus.
result Monolingual paraphrasing outperforms unsupervised translation in all settings.
The paper investigates instance-based interpretation methods for VAEs.
problem Understanding how VAEs make predictions without supervision.
method Formally framed influence functions for VAEs and developed VAE-TracIn.
result Varying training samples significantly impacts VAE predictions.
DIVA clusters dynamic data without needing cluster count, outperforming baselines.
problem Clustering complex, dynamic data without prior knowledge of cluster count.
method Nonparametric Dirichlet Process Mixtures with memoized online variational inference.
result DIVA outperforms state-of-the-art in classifying complex data with changing features.
Enhances graph modeling with hyperbolic geometry and variational inference.
problem Challenges in modeling relational data with complex dependencies.
method Semi-implicit hierarchical variational Bayes with Poincaré embedding and mutual information regularization.
result Improves graph representation quality and flexibility in edge prediction and node classification.
Generative models improve causal effect estimation from observational data.
problem Estimating causal effects from observational data, especially when confounding factors are present.
method Proposes a progressive sequence of Variational Auto-Encoder models to learn underlying factors and causal effects.
result Empirical results show superior performance compared to state-of-the-art approaches.
A new VAE model captures hyperspherical data better than the standard Gaussian model.
problem Standard VAEs fail to model data with a latent hyperspherical structure.
method Proposes using a von Mises-Fisher (vMF) distribution for the latent space, leading to a hyperspherical latent space.
result Hyperspherical VAEs outperform standard VAEs in capturing data with a hyperspherical latent structure.
Flexible SC framework converts voices from non-aligned corpora.
problem Limited practical applications of SC due to lack of parallel corpora.
method Variational auto-encoder framework for non-parallel corpora.
result Framework enables spectral conversion without parallel corpora or alignments.
Stein Variational Adaptive Importance Sampling improves IS with SVGD, reducing KL divergence.
problem Improving the efficiency and interpretability of importance sampling.
method Combines Stein variational gradient descent with importance sampling.
result Significantly reduces KL divergence between proposal and target distributions.
Two graph auto-encoders decouple feature propagation from graph convolution layers.
problem Designing efficient graph auto-encoders with fixed receptive fields.
method L-GAE and L-VGAE using linear matrix computation before auto-encoder input.
result Comparable performance to VGAEs with smaller, simpler networks.
New bounds enable training of probabilistic models for deep networks.
problem Training scalable latent variable models for deep networks.
method Introducing new variational bounds for specific output layers of neural networks.
result Analytical bounds for certain output layers allow training without re-parameterization or Monte Carlo approximations.
In this paper we propose a model that combines the strengths of RNNs and SGVB: the Variational Recurrent Auto-Encoder (VRAE). Such a model can be used for efficient, large scale unsupervised learning on time series data, mapping the time series data to a latent vector representation. The model is generative, such that …
MIAEAD detects anomalies in mixed data types.
problem Challenges of heterogeneity in feature subsets for anomaly detection.
method Multiple-Input Variational Auto-Encoder (MIVAE) for simultaneous feature subset anomaly scoring.
result MIVAE outperforms conventional methods and state-of-the-art unsupervised models in AUC score.
Deep learning reconstructs pressure fields and classifies leakage rates in CCS storage sites.
problem Monitoring CO2 leakage in CCS storage sites.
method Variational auto-encoder tailored for pressure field reconstruction and leakage rate classification.
result Uncertainty estimates of predictions illustrated on synthetic data.