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.
DFI maps covariates to latent representations for feature importance.
problem Feature importance when predictors are statistically dependent.
method Disentangled Feature Importance (DFI) using entropic optimal transport.
result DFI yields stable, interpretable, uncertainty-quantified attributions of shared predictive signal.
Latent features learned by deep learning approaches have proven to be a powerful tool for machine learning. They serve as a data abstraction that makes learning easier by capturing regularities in data explicitly. Their benefits motivated their adaptation to relational learning context. In our previous work, we introdu…
CSVAE learns interpretable latent subspaces for binary labels.
problem Learning interpretable latent representations correlated to specific labels.
method Conditional Subspace VAE (CSVAE) using mutual information minimization.
result CSVAE extracts interpretable latent subspaces for binary labels.
Generative Kernel PCA explores latent spaces for data interpretation and novelty detection.
problem Exploring latent spaces of datasets for better data interpretation.
method Generative Kernel PCA using hidden and visible units similar to Restricted Boltzmann Machines.
result Gradually moving in the latent space allows for interpretation of components and detection of novel patterns.
New framework for explainable AI on high-dimensional data.
problem Challenges in explainability with high-dimensional data.
method Two modules: latent representation and Shapley paradigm adaptation.
result Interpretable model explanations for high-dimensional data.
Proposes a model to decompose feature-level variation in high-dimensional data.
problem Interpreting complex high-dimensional data for understanding feature-level variability.
method Covariate Gaussian Process Latent Variable Model (c-GPLVM) for structured kernel decomposition.
result Extracts low-dimensional structures from high-dimensional data sets while explaining feature-level variability.
New algorithm disentangles latent features without strict assumptions.
problem Disentangling complex data-generating mechanisms into causally interpretable latent features.
method Linear CRL algorithm with topological ordering, pruning, and disentanglement.
result Recovering latent causal features up to an equivalence class under weaker assumptions.
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.
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…
New method explains deep model decisions by adding latent features.
problem Limitations of existing local explanation methods for deep models.
method Leveraging latent features for contrastive local explanations.
result Quantitatively superior explanations on diverse datasets.
Proposes a flexible feature allocation model for sparse factor analysis.
problem Sparse data and rigid assumptions in traditional exploratory tools.
method Adaptive latent feature sharing with control over feature sparsity.
result Derives a novel adaptive Factor analysis (aFA) and aPPCA for flexible dimensionality reduction.
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.
New method interprets neural agent's actions to prevent unwanted outcomes.
problem Blackbox issue in RL where agents learn without foreseeing all outcomes.
method Action-conditional β-VAE for disentangled representation learning.
result Interpretable latent features enable modeling entire state space.
BatchTopK SAEs improve GPT-2 and Gemma activations with adjustable sparsity.
problem Interpreting language model activations using sparse autoencoders.
method Adapting the TopK constraint to the batch-level, allowing variable number of active latents per sample.
result BatchTopK SAEs consistently outperform TopK SAEs in reconstructing GPT-2 and Gemma activations.
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.
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.
Bayesian TNKMs automatically infer model complexity and feature relevance.
problem Manual tuning of TN rank and feature dimensions is error-prone and computationally expensive.
method Bayesian approach with hierarchical priors on TN factors for automatic rank and feature selection.
result Superior performance in prediction accuracy, uncertainty quantification, interpretability, and scalability.
Latent feature modeling allows capturing the latent structure responsible for generating the observed properties of a set of objects. It is often used to make predictions either for new values of interest or missing information in the original data, as well as to perform data exploratory analysis. However, although the…
A new model predicts network events with improved accuracy and interpretability.
problem Predicting and understanding complex dynamic relational data in networks.
method Mutually Exciting Latent Space Hawkes (LSH) model for continuous-time networks.
result The LSH model outperforms existing models in prediction accuracy and interpretability.
Scalable model learns from mixed data groups.
problem Heterogeneous data affecting predictive models and interpretability.
method Joint learning of feature distributions, regression models, and latent group labels.
result Effective in high dimensions, combining data reduction and re-weighting.
The key idea of variational auto-encoders (VAEs) resembles that of traditional auto-encoder models in which spatial information is supposed to be explicitly encoded in the latent space. However, the latent variables in VAEs are vectors, which can be interpreted as multiple feature maps of size 1x1. Such representations…
New method for visualizing high-level concepts in generative models.
problem Challenges in evaluating and visualizing concepts in generative models.
method Introduces a method to compute concept saliency maps for latent representations of known or novel high-level concepts.
result Concept saliency maps highlight input features important for high-level concepts.
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.
Deep neural networks have been shown to be very successful at learning feature hierarchies in supervised learning tasks. Generative models, on the other hand, have benefited less from hierarchical models with multiple layers of latent variables. In this paper, we prove that hierarchical latent variable models do not ta…
Study of urban lifestyles from mobility data of 1.2M people in 11 U.S. cities.
problem Lack of interpretability in digital mobility data for understanding urban lifestyles.
method Privacy-enhanced dataset of mobility visitation patterns, latent activity behavior decomposition.
result Detected 12 latent activity behaviors that describe urban lifestyles, not single lifestyles.
Plug-in method decomposes latent representations into interpretable factors.
problem Decomposing latent representations in neural networks without altering the original models.
method Factors' Decomposer-Entangler Network (FDEN) that learns to decompose latent representations into mutually independent factors.
result FDEN framework effectively decomposes latent representations into interpretable factors, maintaining original model integrity.
Improved neural population modeling using shared features and ensemble detection.
problem Missing shared coding properties in neural latent variable models.
method Feature sharing across tuning curves and soft clustering of neurons.
result More interpretable and better-performing neural population models.
New method interprets object representations from human behavior.
problem Understanding how mental object representations relate to human behavior.
method Sparse, non-negative representations of objects estimated from behavioral judgments.
result Representations predict latent object similarity and are interpretable.
Within a supervised classification framework, labeled data are used to learn classifier parameters. Prior to that, it is generally required to perform dimensionality reduction via feature extraction. These preprocessing steps have motivated numerous research works aiming at recovering latent variables in an unsupervise…
Method determines latent dimensionality in international trade flows.
problem Finding meaningful low-dimensional latent features in high-dimensional international trade data.
method Proposes a latent dimension determination method based on clustering of nonnegative RESCAL decompositions.
result Validates the latent features against empirical economic facts.
A new algorithm learns causal relationships from multimodal data.
problem Discovering causal relationships in exploratory settings without prior information.
method causalPIMA algorithm using multimodal data and physics constraints.
result Learned causal structure and key features in fully unsupervised settings.
New feature mapping approach improves recommendation accuracy and explainability.
problem Balancing recommendation accuracy and explainability using metadata.
method Maps uninterpretable features to interpretable aspect features, minimizing both prediction and interpretation losses.
result Strong performance in recommendation and explainability, eliminating metadata need.
Proposes a new model for explainable recommendation systems.
problem Developing predictive models that provide explanations for item recommendations.
method Generalized Additive Models with Manifest and Latent Interactions (GAMMLI).
result Advantages in both predictive performance and explainability.
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.
DHRL learns interpretable features from visual data.
problem Limited use of deep learning in basic research for interpretable features.
method Generative model chaining, ladder network architecture, latent space regularization.
result DHRL generates disentangled hierarchical features from small datasets.
Enhances FA framework for heterogeneous data with feature selection and semi-supervised learning.
problem Feature extraction and latent representation of heterogeneous data.
method Sparse Semi-supervised Heterogeneous Interbattery Bayesian Analysis (SSHIBA) framework.
result SSHIBA outperforms state-of-the-art algorithms and shows interpretability gains.
New model separates images into independent factors quickly and easily.
problem Separating high-dimensional data like images into independent latent factors.
method Combines bijective feature maps with linear ICA model on the Stiefel manifold.
result Models converge quickly and achieve better unsupervised latent factor discovery.
Generative model for morphological continuum of normal and pathological states.
problem Identifying trends and features that separate normality and pathology in biomedical images.
method Wasserstein Auto-encoder with HSIC regularization for latent features.
result Model generates a continuum of morphological changes corresponding to side information.
ICAM creates interpretable feature attribution maps for brain images.
problem Challenges in predicting class relevance from brain images due to heterogeneity and background variation.
method A VAE-GAN framework for disentangling class relevance from background features.
result FA maps generated by ICAM outperform baseline methods and support phenotype variation exploration.
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.
We present a probabilistic framework for overlapping community discovery and link prediction for relational data, given as a graph. The proposed framework has: (1) a deep architecture which enables us to infer multiple layers of latent features/communities for each node, providing superior link prediction performance o…
Unified approach for interpretable regression with flexible modeling.
problem Combining predictive adaptivity with interpretability in heterogeneous data.
method Combining random Fourier features, spectral feature map, principal component analysis, Gaussian mixture model, and cluster-specific generalized additive models.
result Consistently improves upon classical and black-box models across benchmark datasets.
Adaptive probabilistic PCA adapts complexity with varying subspaces.
problem Adaptive probabilistic PCA models varying complexity in data.
method Relaxed linear Gaussian model with discrete latent variables, Bayesian nonparametric approach.
result Proposes locally adaptive probabilistic PCA (A-PPCA) for varying subspaces.
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…
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.
Unified framework interprets SSL models, revealing biases.
problem Interpreting black-box SSL models for transparency.
method KREPES framework using Representer Landmarks and Nyström approximation.
result Direct audit of SSL latent space without supervision.
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.