New method uses cycle consistency to enforce invariance in latent space.
problem Learning meaningful and independent factors of variation in datasets.
method Two separate latent subspaces, cycle consistency constraints, deep information bottleneck.
result Identifies more meaningful factors leading to sparser and interpretable models.
A new model designs molecules with desired properties.
problem Finding molecules with optimal chemical or biological properties.
method A latent prompt Transformer model with three components: latent vector, molecule generation, and property prediction.
result The model achieves state-of-the-art performance on molecule design tasks.
Unsupervised learning of latent object properties from interactions.
problem Discovering latent physical properties of objects without labeled data.
method Perception-Prediction Network (PPN) framework.
result PPN can accurately simulate and translate latent object properties.
New graph model handles cycles and latent variables.
problem Models for cycles and latent variables.
method Directed graphs with hyperedges (HEDGes), Markov properties.
result Markov properties for HEDGes are not equivalent.
Proposes a new prior for deep generative models to capture latent properties.
problem Complex non-linear relationships between data and latent properties.
method Factorial mixture prior with Gaussian mixture models for quantization.
result Empirically evaluated method for learning discrete properties in unsupervised or semi-supervised settings.
Paper proposes a method to design molecules with specific properties.
problem Designing molecules with desired chemical and biological properties.
method Energy-based model in latent space, SGDS algorithm for gradual distribution shifting.
result Method achieves strong performances on various molecule design tasks.
New approach identifies latent properties from mechanisms, not just data.
problem Identifying latent properties from data generating processes.
method Equivariance perspective on identifiable representation learning.
result Identification of latent properties is possible up to shared equivariances in known mechanisms.
TLR learns better latent representations for unsupervised domain adaptation.
problem Learning models in a target domain using data from a source domain.
method Designing a simple linear autoencoder objective function to derive robust latent representations.
result TLR reduces domain shift and preserves common properties of both domains.
Diffusion Variational Autoencoders capture topological properties of datasets.
problem Standard VAEs struggle with topological properties of certain datasets.
method Introduces Diffusion VAEs with transition kernels of Brownian motion on arbitrary manifolds.
result Diffusion VAEs can capture topological properties of synthetic datasets.
Paper recovers latent causal structure and linear transformation from indirect observations.
problem Recovering latent causal structure and linear transformation from indirect observations.
method Established sufficient conditions for DAG recovery, leveraged score function properties, and used soft/hard interventions.
result Perfect recovery of latent DAG structure and linear transformation up to scaling using soft interventions, hard interventions with additional hypothesis testing.
A new model designs molecular latent vectors for drug discovery.
problem Designing effective molecular descriptors from molecular structures.
method Proposes a denoising diffusion probabilistic model (DDPM) for variational autoencoding molecular graphs.
result Demonstrates superior prediction performance and robustness compared to existing approaches.
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…
Study shows latent space OOD detection isn't a reliable proxy for model performance.
problem Evaluating and interpreting deep learning systems on real-world data.
method Empirical investigation of latent space OOD detection and classification accuracy using SAR datasets.
result OOD detection cannot be used as a proxy measure for model performance.
New method uses Diffusion Maps for latent space modeling of dynamical systems.
problem Building reduced dynamical models from time series data.
method Two rounds of Diffusion Maps on latent coordinates, with lifting back to ambient space.
result Approximation of full state functions in reduced coordinates.
SyNGLER generates synthetic networks efficiently while preserving key structural properties.
problem Efficiently generating realistic synthetic networks with preserved structural properties.
method SyNGLER uses latent space network models to learn and reconstruct node embeddings, then generates synthetic networks.
result SyNGLER produces synthetic networks that better preserve key network characteristics than existing approaches.
Enhances autoencoders to represent transformations explicitly.
problem Lack of explicit representation of transformations in autoencoders.
method Extended variational autoencoders to include latent transformations, using hierarchical graphical models.
result Inferred latent transformations reflect interpretable properties in the observation space.
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.
This study improves GANs by learning latent distributions and pushforward maps.
problem Improving the performance of GANs with optimal transport metrics.
method Focuses on the interplay between latent distribution and generator complexity.
result Learning latent distributions and pushforward maps can significantly reduce sample complexity.
The study examines issues with latent distributions in generative models and proposes using Cauchy distribution.
problem Issues with latent distributions causing mismatch in sampled regions during linear interpolations.
method Proposed using multidimensional Cauchy distribution and two methods for creating non-linear interpolations.
result Linear interpolations may generate unrealistic data due to the Central Limit Theorem, and Cauchy distribution mitigates this issue.
All SMILES VAE learns molecule latent representations from SMILES strings.
problem Non-unique SMILES strings and high computational cost of graph convolutions hinder VAEs for molecular property optimization.
method Stacked recurrent neural networks encode multiple SMILES strings, pooling hidden representations, and attentional pooling builds a final latent representation.
result All SMILES VAE significantly surpasses state-of-the-art in molecular property optimization tasks.
Generative model creates drug-like molecules with multiple properties.
problem Designing molecules with multiple desired properties.
method Conditional Variational Autoencoder (VAE) in latent space control.
result Can generate drug-like molecules with five target properties.
A new autoencoder framework transforms latent space to improve generative and denoising models.
problem Improving the performance of generative and denoising models in autoencoders.
method Homeomorphic transformation of latent variables to reduce distance and preserve topological properties.
result The transformed latent space leads to better performance in generative and denoising models, as measured by Hausdorff distance and visual characteristics.
Autoencoder optimizes data embedding for accurate PDF reproduction.
problem Inaccurate PDF reproduction in latent space of VAEs.
method Rate-Distortion Optimization guided autoencoder with isometric property.
result Our method achieves isometric data embedding and tractable PDF relations.
VAEs help in learning latent variables for cryo-EM applications.
problem Learning latent variables for cryo-EM data.
method Used VAEs for latent variable learning, focusing on the encoder's role.
result The encoder of the VAE in cryo-EM applications resembles traditional latent variable representations.
Paper proposes a new model for disentangled latent representations using copula transformations.
problem Disentanglement of latent features in deep latent variable models.
method Adopted deep information bottleneck model, applied copula transformation to restore invariance and sparsity.
result The new model achieves disentanglement and sparsity of latent features.
Generative autoencoders help create new molecular structures.
problem Generating novel molecules with desirable properties.
method Used autoencoders to map molecule structures into a latent space and back.
result The latent space preserves chemical similarity and can generate new compounds.
Generative model connects physical properties to latent vectors for solar magnetic patches.
problem Disconnection between generative latent vectors and scientifically relevant quantities.
method Integrating GAN, SVM, and SSL to generate and retrieve physically interpretable solar magnetic patches.
result GAN-SVM combination enables smooth changes in physical parameters with generated patches.
Reformulates Wasserstein autoencoder for hyperbolic latent space.
problem Learning structured latent representations on non-Euclidean manifolds.
method Uses Poincaré ball model of hyperbolic space for latent space structure.
result Competitive results on graph link prediction task.
Tutorial on combining latent variable models with deep learning.
problem Combining latent variable models with deep learning to model natural language.
method Exploring variational inference to address intractable posterior inference and non-differentiability issues.
result Exploration of variational inference techniques to handle deep latent variable models.
Improved VAE representations lead to better image classification.
problem VAE representations are inferior to non-latent models for image classification.
method Used a decoder that prefers local features, improving global feature capture in latent variables.
result Significant improvement in downstream semantic classification tasks.
MoFlow generates chemically valid molecular graphs from latent representations.
problem Generating chemically valid molecular graphs from latent representations is challenging.
method MoFlow uses a flow-based approach with Glow for bond generation and a novel graph conditional flow for atom generation, ensuring chemical validity and efficiency.
result MoFlow achieves state-of-the-art performance in molecular graph generation and optimization.
PFM generates novel samples on data manifolds using pullback geometry.
problem Generating novel samples on complex data manifolds.
method Pullback Flow Matching framework leveraging pullback geometry and isometric learning.
result PFM achieves improved manifold learning and generative performance.
Developed DLCM for more accurate clustering of categorical data.
problem Restrictive conditional independence assumption in traditional LCMs.
method Bayesian Dependent Latent Class Model (DLCM) that allows conditional dependence.
result DLCMs are effective in applications with time series, overlapping items, and structural zeroes.
DSVNP uses global and local latent variables for improved neural process predictions.
problem Limited expressiveness of vanilla neural processes in capturing target-specific local variation.
method Introduces DSVNP combining global and local latent variables for prediction.
result Competitive prediction performance in multi-output regression and uncertainty estimation.
GraphOpt learns the formation mechanism of graphs from observed structures.
problem Learning formation mechanisms from observed graphs with complex structural properties.
method GraphOpt uses maximum entropy inverse reinforcement learning to solve the link formation problem in a sequential decision-making process.
result GraphOpt discovers a latent objective function that can explain and transfer across different graphs.
Heteroencoders improve chemical latent space diversity and molecular generation.
problem Improving chemical latent space properties and diversity in autoencoders.
method Employing SMILES enumeration for encoder or decoder, training RNNs with LSTM, and using QSAR models.
result Heteroencoders yield more diverse latent spaces and better molecular generation.
Confidence-based filtering reveals latent structure in diffusion models.
problem Unclear latent structure in diffusion models.
method Confidence scores from a classifier.
result Class-relevant latent structure emerges under confidence-based filtering.
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.
Bayesian model for analyzing mixed data types.
problem Automatic exploratory analysis of heterogeneous datasets.
method General Bayesian non-parametric latent feature model.
result Automatic inference of model complexity and binary-valued latent features.
Paper develops robust methods for panel data with latent groups, improving inference under group separation violations.
problem Inference in latent group panel models under group separation violations.
method Selective conditional inference approach to derive conditional distribution of coefficients given estimated group structure.
result Valid inference under violations of group separation, superior to traditional asymptotic methods.
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.
New method identifies stable latent variables across different domains using weak distributional invariances.
problem Learning causal representations for multi-domain datasets.
method Autoencoders incorporating weak distributional invariances.
result Autoencoders can identify stable latent variables across different domains.
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…
Domain adaptation framework identifies latent variables for target distribution identifiability.
problem Unsupervised domain adaptation without identifiable joint distribution of features and labels.
method Formulated latent variable model with invariant and changing components, constrained domain shift to influence only changing components.
result Joint distribution of data and labels in target domain is identifiable under mild conditions.
TALBO optimizes latent spaces for evolving design objectives.
problem Temporal drift in design objectives.
method GP-prior variational autoencoder for time-varying latent space.
result Consistently outperforms LSBO baselines across varying drift speeds and objectives.
PRESTO maps latent representations across diverse ML models.
problem Understanding variability in latent representations across different ML models.
method Uses persistent homology to characterize latent spaces and measure their pairwise similarity.
result Preserves desirable properties and enables sensitivity analysis of latent representations.
Develops SCMs for latent selection to simplify causal analysis.
problem Latent selection complicates causal analysis.
method Introduces a conditioning operation for SCMs to encode latent selection.
result Conditioning operation preserves simplicity, acyclicity, and linearity of SCMs.
We study a norm for structured sparsity which leads to sparse linear predictors whose supports are unions of prede ned overlapping groups of variables. We call the obtained formulation latent group Lasso, since it is based on applying the usual group Lasso penalty on a set of latent variables. A detailed analysis of th…