Improved DSSMs for easier interpretable latent variables.
problem Complex and hard-to-interpret latent variables in DSSMs.
method Simplified predictive decoder and shrinkage priors.
result Interpretable latent variables improve forecasting performance.
Method interprets GAN latent space via latent variable correlation analysis.
problem Understanding the inner workings of GANs.
method Analyzing correlation between latent variables and semantic contents in generated images.
result A method for controllable semantic content generation in GANs.
Enhances interpretability of linear latent spaces through automated clustering and ranking.
problem Severe interpretability issues in latent directions of PCA, ICA, CCA, and FA.
method LS-PIE framework automates clustering and ranking of latent vectors.
result Enhanced interpretability of latent vectors through LR, LS, LC, and LCON.
A neural network finds causal relationships among latent variables.
problem Learning causal structure among latent variables in high-dimensional data.
method Redundant Input Neural Network (RINN) with modified architecture and regularized objective function.
result The RINN method successfully recovers latent causal structure between input and output variables.
Improves latent variable learning for complex data.
problem Expressive latent variables for model prediction on multi-component data.
method Dynamic Latent Separation method that distances data samples in the latent space.
result Enhances output diversity and provides interpretable representations.
Study improves interpretability in generative models by disentangling latent variables in scientific datasets.
problem Extracting generative factors from complex, high-dimensional datasets in unsupervised or semi-supervised settings.
method Introducing Aux-VAE, a novel architecture within the VAE framework, which disentangles latent variables by guiding them with auxiliary variables.
result Aux-VAE achieves disentanglement with minimal modifications to the standard VAE loss function, validated on multiple datasets.
pi-VAE models neural activity with interpretable latent variables.
problem Difficult interpretation of deep generative models for neural data.
method Adapted variational auto-encoder to integrate task variables.
result Improves interpretability and identifiability of neural codes.
spex-LVM infers interpretable latent factors from biomedical data.
problem Inability to learn sparse and interpretable hidden states.
method Factorial latent variable model with sparse priors and domain-relevant annotations.
result Robustly identifies relevant structure in RNA-seq datasets.
After deep generative models were successfully applied to image generation tasks, learning disentangled latent variables of data has become a crucial part of deep generative model research. Many models have been proposed to learn an interpretable and factorized representation of latent variable by modifying their objec…
Paper detects hierarchical changes in latent variable models from data streams.
problem Detecting changes at three levels: data distribution, latent variables, and number of latent variables.
method Information-theoretic framework using MDL and DNML for change detection.
result Effective in detecting changes with good interpretability.
DICCA maps multi-view data into a shared latent space with interpretable components.
problem Learning from multiple related but distinct data views.
method DICCA extends CCA to deep generative networks and uses sparsity-inducing priors for interpretability.
result DICCA effectively disentangles shared and view-specific variations in multi-view data.
Improved robust latent variable estimation for neural dynamics.
problem Inconsistent results due to noise and nonlinearity in existing models.
method Probabilistic approach to latent variable estimation in decomposed models.
result More accurate latent variable inference in nonlinear systems with diverse noise conditions.
Framework learns image dynamics between time steps using latent variables.
problem Challenges in capturing evolving image patterns and temporal information.
method Estimates intermediary image stages using a physical latent variable model.
result Demonstrates robustness and effectiveness in geoscientific imagery.
SPLICE method disentangles shared and private latent variables from multi-view data.
problem Lack of methods to characterize nonlinear relationships and preserve geometric information in multi-view data.
method Neural network-based approach to infer disentangled, interpretable representations of shared and private latent variables.
result SPLICE yields more interpretable representations by preserving geometry and is more robust to incorrect latent dimensionality.
New method identifies latent relationships in deep models without additional constraints.
problem Latent representations in deep latent variable models are not statistically identifiable.
method Identifies relationships between latent variables (distances, angles, volumes) under mild model conditions.
result Empirically demonstrates more reliable latent distances without additional labeled data.
LaCIM avoids spurious correlation by modeling latent causal factors.
problem Avoiding spurious correlation in supervised learning.
method Introducing latent variables for causal prediction and optimizing over latent space.
result Improved interpretability, robustness, and prediction power on OOD scenarios.
Software helps teach latent variable methods in multivariate data analytics.
problem Challenges in understanding multivariate data analytics for students.
method Interactive software for comparing latent variable methods.
result Builds intuition on choosing methods and interpreting coefficients.
DCRL learns causal relationships from mixed-type discrete data.
problem Challenges in learning causal relationships from discrete, mixed-type data.
method Generative framework modeling directed acyclic graph and sparse bipartite graph, flexible measurement models for different types of data.
result Consistent recovery of latent causal structure from observed data distribution.
MuVI models multi-view data with structured sparsity, integrating domain knowledge.
problem Disentangling variation across multiple data views in complex systems.
method Multi-view latent variable model with structured sparsity using a modified horseshoe prior.
result MuVI outperforms state-of-the-art methods in structured sparsity modeling and integrates noisy domain expertise.
Proposes a framework to improve VAE latent codes using mutual information.
problem Lack of explicit measure for VAE latent variable quality.
method Variational Mutual Information Maximization Framework.
result Improves relationships between latent codes and observations.
In this work we present Discrete Attend Infer Repeat (Discrete-AIR), a Recurrent Auto-Encoder with structured latent distributions containing discrete categorical distributions, continuous attribute distributions, and factorised spatial attention. While inspired by the original AIR model andretaining AIR model's capabi…
Simultaneous Latent Budget Trees for stratified classification
problem Classification with stratification factors
method Probabilistic machine learning framework
result Interpretation of latent components and conditional split rule
Method evaluates disentanglement in DLVMs, including those not aligned with latent axes.
problem Evaluate disentanglement in DLVMs, especially those not aligned with latent axes.
method Proposes a statistical method to discover generative factors of a dataset.
result Empirically demonstrates the advantage of the method on two datasets.
CRL uses causality to build interpretable AI models from complex data.
problem Interpreting deep neural networks' implicit representations.
method Causal representation learning (CRL) synthesizing latent variable models, causal graphical models, and nonparametric statistics.
result CRL can improve interpretability of generative AI models.
Using the linear Gaussian latent variable model as a starting point we relax some of the constraints it imposes by deriving a nonparametric latent feature Gaussian variable model. This model introduces additional discrete latent variables to the original structure. The Bayesian nonparametric nature of this new model al…
Neural Decomposition breaks down VAE latent structure for better interpretability.
problem Limited interpretability of VAE latent representations.
method Adapted functional ANOVA to VAEs, applying constraints for identifiability.
result Decomposes data variation into latent and fixed input effects.
A method estimates causal parameters using a latent variable recovery.
problem Estimating causal parameters in contexts with multiple causes and unobserved confounding.
method Substitute adjustment via recovery of latent variables.
result Substitute adjustment estimates adjusted regression parameters under certain conditions.
Recurrent-DBN models dynamic relational data with interpretable latent structures.
problem Interpreting dynamic relational data with hidden structures.
method Recurrent Dirichlet Belief Network framework with hierarchical latent structures and efficient inference strategy.
result Recurrent-DBN discovers interpretable latent structures and improves link prediction.
Powerful generative models, particularly in Natural Language Modelling, are commonly trained by maximizing a variational lower bound on the data log likelihood. These models often suffer from poor use of their latent variable, with ad-hoc annealing factors used to encourage retention of information in the latent variab…
This work extends identifiability analysis to sequential latent variable models, focusing on Switching Dynamical Systems.
problem Identifying latent variables in sequential data models.
method Proved identifiability of Markov Switching Models and established conditions for Switching Dynamical Systems.
result Identifiability of latent variables and non-linear mappings in Switching Dynamical Systems up to affine transformations.
This paper proposes a hierarchical, fine-grained and interpretable latent variable model for prosody based on the Tacotron 2 text-to-speech model. It achieves multi-resolution modeling of prosody by conditioning finer level representations on coarser level ones. Additionally, it imposes hierarchical conditioning across…
New method predicts heat load in thermal grids using latent variables.
problem Predicting heat load in district energy systems.
method Combines nominal model for outdoor temperature with latent variable model for residual heat load.
result Proposed method achieves better prediction accuracy than artificial neural networks.
The interpretation of complex high-dimensional data typically requires the use of dimensionality reduction techniques to extract explanatory low-dimensional representations. However, in many real-world problems these representations may not be sufficient to aid interpretation on their own, and it would be desirable to …
Develops identifiability theory for multi-lag regime-switching models.
problem Ensuring interpretability of deep latent variable models with multi-lag dependencies.
method Formulates a general theoretical framework for multi-lag Regime-Switching Models (RSMs), proving identifiability of number of regimes and multi-lag transitions.
result Establishes identifiability conditions for multi-lag regime-switching models, including Markov Switching Models and Switching Dynamical Systems.
We present a novel method for hierarchical topic detection where topics are obtained by clustering documents in multiple ways. Specifically, we model document collections using a class of graphical models called hierarchical latent tree models (HLTMs). The variables at the bottom level of an HLTM are observed binary va…
SAMS-VAE models cellular perturbations using sparse additive mechanisms.
problem Modeling effects of diverse interventions on cells.
method Sparse Additive Mechanism Shift Variational Autoencoder (SAMS-VAE).
result SAMS-VAE identifies disentangled, perturbation-specific latent subspaces.
ACE models allow flexible conditioning and prediction of latent variables.
problem Lack of flexibility in conditioning and prediction of latent variables in probabilistic models.
method Introduces Amortized Conditioning Engine (ACE) that explicitly represents latent variables and allows runtime conditioning and prediction.
result ACE models outperform existing methods in diverse tasks like image completion, classification, Bayesian optimization, and simulation-based inference.
Proposes LVGP for multi-source data fusion in science and engineering.
problem Differences in quality and comprehensiveness of data sources.
method Latent Variable Gaussian Process (LVGP) framework.
result Improved predictions for sparse-data problems.
OracleAD detects multivariate time series anomalies without labels.
problem Rare and unlabeled multivariate time series anomalies.
method OracleAD encodes past sequences into causal embeddings, projects them into a latent space, and identifies anomalies based on deviations from a stable latent structure.
result OracleAD achieves state-of-the-art results and is interpretable.
Learning attribute applicability of products in the Amazon catalog (e.g., predicting that a shoe should have a value for size, but not for battery-type at scale is a challenge. The need for an interpretable model is contingent on (1) the lack of ground truth training data, (2) the need to utilise prior information abou…
This paper introduces a general Bayesian non- parametric latent feature model suitable to per- form automatic exploratory analysis of heterogeneous datasets, where the attributes describing each object can be either discrete, continuous or mixed variables. The proposed model presents several important properties. First…
Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning. Specifically, designing models with tractable learning, sampling, inference and evaluation is crucial in solving this task. We extend the space of such models using real-valued non-volume preserving (real NVP) transf…
While a wide range of interpretable generative procedures for graphs exist, matching observed graph topologies with such procedures and choices for its parameters remains an open problem. Devising generative models that closely reproduce real-world graphs requires domain knowledge and time-consuming simulation. While e…
This work proposes a new method to train models with deep latent hierarchies using Optimal Transport.
problem Training models with deep latent hierarchies using VAEs often leads to the 'latent variable collapse' issue.
method Proposes a novel approach based on Optimal Transport to train models with deep latent hierarchies.
result The method avoids the 'latent variable collapse' issue and provides better sample generations and latent representation.
Deep equilibrium models estimate latent variables from data.
problem Estimating latent variables from data.
method Generalized exponential family models, deep equilibrium networks.
result Deep equilibrium models solve MAP estimates for latent and transformation parameters.
As a popular tool for producing meaningful and interpretable models, large-scale sparse learning works efficiently when the underlying structures are indeed or close to sparse. However, naively applying the existing regularization methods can result in misleading outcomes due to model misspecification. In particular, t…
Improved neural network model for predicting latent budgets in compositional data.
problem Predicting response variables in compositional data with non-negativity constraints.
method LBA-NN, a feed forward neural network model that incorporates K-means clustering for interpretation.
result LBA-NN outperforms traditional LBA in prediction accuracy, specificity, recall, and mean square error.
Paper uses VAEs to control IVS features for financial modeling.
problem Generating realistic IVSs with desired characteristics.
method Variational autoencoder architecture with controllable latent variables.
result Controlled generation of IVSs with specified features.