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.
Unified framework for disentangled VAEs improves latent space interpretability.
problem Challenges in evaluating and interpreting latent representations, especially for diverse data types.
method Unified bfVAE framework, FVH-LT, DBSR-LS, GAS, LSSI.
result bfVAE provides more favorable trade-off between disentanglement and reconstruction.
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.
Fractal Flow enhances normalizing flows with interpretable latent space and hierarchical modeling.
problem High-dimensional density estimation and generative modeling challenges.
method Integrates topic modeling (LDA) and fractal strategy into normalizing flows.
result Achieves latent clustering, controllable generation, and superior estimation accuracy.
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…
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.
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.
FLANs process each feature separately for better interpretability.
problem Need for interpretable machine learning models in critical scenarios.
method Feature-wise latent representations summed for prediction.
result FLANs enhance interpretability without sacrificing performance.
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.
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.
Proposes a VAE with a discrete bottleneck for better text generation.
problem VAEs struggle with latent variable auto-regressive decoding in text generation.
method Introduces a discretized bottleneck to enforce latent feature matching in a compact space.
result Demonstrates improved text generation capabilities across various tasks.
Study evaluates interpretability of time series foundation models' latent spaces.
problem Improving interpretability of latent spaces in time series models for visual analytics.
method Evaluated MOMENT family of transformer-based models on five datasets, fine-tuning for performance.
result Fine-tuning improved latent space clarity but limited interpretability remained.
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.
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.
UT module refines VAE latent space, improving disentanglement and interpretability.
problem Irregular latent distributions cause posterior collapse and misalignment in VAEs.
method UT module uses G-KDE clustering, GM modeling, and PIT to transform latent space into uniform distribution.
result UT module enhances disentanglement and interpretability of latent representations.
Geometric interpretation improves VAE performance and robustness.
problem Improving Variational Autoencoder performance and robustness.
method Introducing a geometric perspective on VAEs, sampling from the Riemannian latent space.
result Improved generation and interpolations with competitive or better performance on benchmark datasets.
ADHAM provides interpretable survival analysis for healthcare.
problem Limited interpretability in deep learning survival models.
method Additive Deep Hazard Analysis Mixtures (ADHAM) with latent subgroup structure.
result ADHAM offers interpretable insights into exposure-outcome associations.
This text explores strategies for learning discrete latent structures in neural networks.
problem Learning discrete latent structures in neural networks is challenging.
method Continuous relaxation, surrogate gradients, and probabilistic estimation.
result Many latent structure learning strategies use the same fundamental building blocks but apply them differently.
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.
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.
Cryo-em images are found to be low-dimensional.
problem Understanding the geometric structure of cryo-em data.
method Applied manifold learning techniques to CryoSBI representations.
result Cryo-em data inherently populate low-dimensional manifolds.
Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of unsupervised learning of features correlated to specific labels in a dataset. We propose a …
The paper proposes a method to estimate latent structures in multivariate data without assuming their existence.
problem Estimating latent structures in multivariate distributions that are difficult to identify and reflect the data generating mechanism.
method A model-free approach using a multiscale nonparametric maximum likelihood estimator.
result The method captures meaningful discrete structure at different scales and integrates them to yield an interpretable discrete representation.
AR-Flow VAE improves blind source separation with flexible autoregressive priors.
problem Unsupervised blind source separation of latent signals from mixtures.
method AR-Flow VAE uses autoregressive flows to model latent sources, enhancing flexibility and capturing complex dependencies.
result AR-Flow VAE effectively separates latent sources, demonstrating improved performance over conventional methods.
Deep generative models have recently yielded encouraging results in producing subjectively realistic samples of complex data. Far less attention has been paid to making these generative models interpretable. In many scenarios, ranging from scientific applications to finance, the observed variables have a natural groupi…
StrADiff separates sources from mixtures without labels, using structured priors.
problem Blind source separation of linear and nonlinear mixtures without labeled data.
method Structured Source-Wise Adaptive Diffusion Framework with Gaussian process priors.
result StrADiff can recover latent source trajectories in an unsupervised manner, especially stable in linear mixtures.
Interprets how intrinsic motivation shapes behavior in RL agents.
problem Understanding how intrinsic motivation influences behavior in reinforcement learning agents.
method Analyzed five RL agents in procedurally generated environments using various interpretability techniques.
result Curiosity-driven agents exhibit broader and more dynamic attention than extrinsically motivated agents.
Paper introduces models to discover complex structures in large hypergraphs.
problem Understanding dependency structures in complex systems represented as hypergraphs.
method Probabilistic models treating classes of similar units as nodes in a latent hypergraph, using low-rank representations.
result Improves link prediction and discovers interpretable structures in diverse real-world systems.
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.
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.
Compositional structures between parts and objects are inherent in natural scenes. Modeling such compositional hierarchies via unsupervised learning can bring various benefits such as interpretability and transferability, which are important in many downstream tasks. In this paper, we propose the first deep latent vari…
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
AMES framework selects optimal embedding space for latent graph inference.
problem No principled method for choosing the best embedding space for latent graph inference.
method Differentiable AMES framework using backpropagation to select optimal embedding space.
result Consistently achieves comparable or superior results across multiple datasets.
Bayesian hypergraph inference models disease pathways from EHR data.
problem Modeling rare diseases influenced by shared risk factors.
method Bayesian hypergraph inference framework reframing multi-disease modeling.
result Interpretable disease pathways and well-calibrated uncertainty quantification.
VDA improves disentanglement of latent representations in complex signals.
problem Learning disentangled and interpretable representations in nonstationary, high-dimensional time-evolving signals.
method Variational decomposition autoencoding (VDA) framework, incorporating signal decomposition, contrastive self-supervised task, and variational prior approximation.
result DecVAEs surpass state-of-the-art VAE-based methods in disentanglement quality and generalization.
SENA-discrepancy-VAE interprets latent causal factors in biological pathways.
problem Interpreting latent causal factors in biological pathways.
method SENA-discrepancy-VAE, a model based on discrepancy-VAE, that produces interpretable latent causal factors.
result Sena-discrepancy-VAE achieves comparable predictive performance with non-interpretable counterparts while providing biologically meaningful causal factors.
Study adapts β-TCVAE for fMRI to recover nonlinear brain components.
problem Capturing nonlinear brain dynamics in fMRI data.
method Adapted β-TCVAE framework for fMRI data. result Recovery of meaningful nonlinear spatial components in fMRI data.
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…
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.
Generative model disentangles dark matter halo properties.
problem Entangling physical factors in generative model latent spaces.
method Auxiliary-variable-guided framework with halo mass and concentration.
result Reveals mass-concentration scaling relation and identifies unusual halo formation.
Originally designed to model text, topic modeling has become a powerful tool for uncovering latent structure in domains including medicine, finance, and vision. The goals for the model vary depending on the application: in some cases, the discovered topics may be used for prediction or some other downstream task. In ot…
This paper presents a Bayesian nonparametric latent feature model specially suitable for exploratory analysis of high-dimensional count data. We perform a non-negative doubly sparse matrix factorization that has two main advantages: not only we are able to better approximate the row input distributions, but the inferre…
IntroVAC learns interpretable latent subspaces for better image quality.
problem Difficulties in interpreting latent spaces and limitations in image generation.
method Introspective Variational Classifier (IntroVAC) using additional labels and adversarial training.
result Improved image quality and meaningful latent directions for fine-grained manipulation.
We develop deep Poisson-gamma dynamical systems (DPGDS) to model sequentially observed multivariate count data, improving previously proposed models by not only mining deep hierarchical latent structure from the data, but also capturing both first-order and long-range temporal dependencies. Using sophisticated but simp…
In variational autoencoders, the prior on the latent codes z is often treated as an afterthought, but the prior shapes the kind of latent representation that the model learns. If the goal is to learn a representation that is interpretable and useful, then the prior should reflect the ways in which the high-level fact…
PRISM-VQ combines financial priors with vector quantization for better stock prediction.
problem Predicting cross-sectional stock returns is hard due to low signal-to-noise ratios and changing market conditions.
method Integrates expert priors, vector-quantized latent factors, and dynamic factor loadings.
result Consistent improvements in cross-sectional return prediction and portfolio performance.
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.