Discrete-AIR model identifies objects in images with interpretable latent codes.
problem Identifying objects in images without labeled data.
method Recurrent Auto-Encoder with structured latent distributions for discrete, continuous, and spatial attention.
result Discrete-AIR model uses minimal latent variables for efficient inference.
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.
Unsupervised framework learns latent codes for controllable generation.
problem Challenging to achieve controllable generation with GANs.
method Self-training iterative feedback from discriminator to generator.
result Better disentanglement and semantic meaningful latent codes.
Paper proposes structured semantic perturbations to improve adversarial attacks.
problem Vulnerability of deep neural networks to adversarial attacks.
method Manipulates semantic attributes via disentangled latent codes.
result Demonstrates the effectiveness of structured semantic perturbations.
A new method for disentangled latent spaces in VAEs that can manipulate attributes.
problem Disentangled representation of attributes in latent spaces of VAEs.
method Attribute-based regularization loss to enforce monotonic relationships between attributes and latent codes.
result Manipulation of attributes in latent spaces post-training.
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.
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.
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.
This paper clarifies VAE's property through geometric and information-theoretic interpretations.
problem The transparency of VAE model is an underlying issue.
method Quantitative understanding of VAE through differential geometry and information theory.
result VAE can be mapped to an implicit isometric embedding with a scale factor derived from the posterior parameter.
This paper introduces a quantization-based regularizer for autoencoders to improve latent representations.
problem Autoencoders can overfit and collapse, leading to poor latent representations.
method The authors combine VQ-VAE and denoising methods to introduce a bottleneck Bayesian estimator that soft quantizes latent codes.
result The method results in better latent representations for supervised and clustering tasks.
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.
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.
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.
PUDLE method analyzes and improves unrolled sparse coding networks for dictionary learning.
problem Dictionary learning problem, representing data as a combination of few atoms.
method PUDLE method addresses challenges in unrolled sparse coding networks through theoretical analysis and practical strategies.
result PUDLE method provides conditions for recovering and preserving the support of the latent code, and resolves bias and instability issues.
Algorithm uncovers latent attribute graph from molecular data.
problem Learning latent representations and interpreting them for limited data.
method Perturbation experiments on latent codes of a generative autoencoder.
result Effective graphical model of latent codes and attributes.
VQShape learns interpretable time-series representations and achieves comparable performance to specialist models.
problem Lack of interpretability in existing time-series models.
method Vector quantization of time-series data into abstracted shapes.
result VQShape achieves comparable performance to specialist models in classification tasks.
MTDS improves sequence generation adaptability via latent code control.
problem Lack of adaptability in sequence generation models like RNNs.
method Hierarchical multi-task dynamical systems (MTDS) with latent code control.
result MTDS enables style transfer, interpolation, and morphing in generated sequences.
Regularized autoencoders learn the latent codes, a structure with the regularization under the distribution, which enables them the capability to infer the latent codes given observations and generate new samples given the codes. However, they are sometimes ambiguous as they tend to produce reconstructions that are not…
We tackle class imbalance in unsupervised domain adaptation using latent codes.
problem Class imbalance in unsupervised domain adaptation where target domain has under-represented classes.
method Adversarial domain adaptation framework with latent codes to identify and estimate target labels.
result Latent codes can disentangle target domain structure and identify under-represented classes.
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…
Proposes a framework to maximize mutual information in VAE models for better latent code representation.
problem Lack of explicit measurement of the quality of learned representations in VAE models.
method Variational Mutual Information Maximization Framework for VAE.
result Maximizes mutual information between latent codes and observations, improving latent code representation.
Improves disentangled GAN training and selection without labeled data.
problem Challenges in training disentangled GANs, especially self-supervision.
method Contrastive Regularizer and ModelCentrality for unsupervised disentanglement.
result Significantly improved disentanglement scores without labeled data.
Auto-decoder synthesizes graphs from latent codes.
problem Creating new graph structures from specified distributions.
method Generative model learns latent codes from empirical distribution. Self-attention identifies likely connectivity patterns. Graph-based normalizing flows sample latent codes.
result Model outperforms state of the art by 1.5x in accuracy and 2x in speed.
Proposes a new model for directed graphs combining deep learning and latent variable models.
problem Graph representation learning for directed graphs.
method Deep Latent Space Model (DLSM) integrating GCN encoder and stochastic decoder with hierarchical variational auto-encoder architecture.
result Achieves state-of-the-art performance on link prediction and community detection tasks.
The paper introduces InfoRL, a method to learn multiple ways to perform tasks in complex environments.
problem Learning a single best policy for tasks in complex environments.
method InfoMax approach to discover multiple latent codes for task performance.
result It is possible to learn multiple ways to perform tasks in complex environments using information maximization.
A new method for image translation without paired data.
problem Image-to-image translation between two domains with content preservation.
method Energy-based model in latent space of pretrained autoencoder.
result Improved translation quality and content preservation.
New insights into BNN optimization redefine latent weights as inertia.
problem Optimizing Binarized Neural Networks (BNNs) with latent weights.
method Interpreted latent weights as inertia and introduced Binary Optimizer (Bop).
result Demonstrated improved performance of Bop on CIFAR-10 and ImageNet.
Deep model learns complex latent codes without assuming factor structure.
problem Learning latent codes with complex, non-factorial distributions.
method Deep generative factor analysis with beta process prior and stochastic EM algorithm.
result Preliminary results show model can approximate complex distributions.
Enhances text generation interpretability with a mixture of exponential family distributions.
problem Limited interpretability in text generation models.
method Introduced Dispersed Exponential Family Mixture VAEs (DEM-VAE) with a mixture of exponential family distributions and an extra dispersion term to train the model.
result Demonstrated improved interpretability and generation quality compared to strong baselines.
Proposes a non-parametric method for deep discrete latent variable models.
problem Learning sparse discrete latent representations in deep models.
method Iterative algorithm with Beta-Bernoulli process prior and local data scaling.
result Improves sparsity and scalability of deep discrete latent variable models.
Many image-to-image translation problems are ambiguous, as a single input image may correspond to multiple possible outputs. In this work, we aim to model a \emph{distribution} of possible outputs in a conditional generative modeling setting. The ambiguity of the mapping is distilled in a low-dimensional latent vector,…
Bit-Swap improves lossless compression for hierarchical latent variable models.
problem Efficient lossless compression for latent variable models with hierarchical structure.
method Generalizes bits-back coding to hierarchical latent variable models with Markov chain structure.
result Achieves superior lossless compression rates for hierarchical latent variable models.
New method compresses facial videos using GANs and latent space optimization.
problem Efficiently compressing facial videos at low bit rates.
method Leverages StyleGAN for latent space representation and compression, learns optimal compression through entropy model and perceptual loss.
result Significantly reduces perceptual distortion at low bit rates compared to state-of-the-art codecs.
Finding compact representation of videos is an essential component in almost every problem related to video processing or understanding. In this paper, we propose a generative model to learn compact latent codes that can efficiently represent and reconstruct a video sequence from its missing or under-sampled measuremen…
PPC detects anomalies in high-dimensional data efficiently.
problem Scalability issues and reduced performance with high-dimensional data.
method Probabilistic Predictive Coding (PPC) learns latent representations and predicts uncertainties.
result PPC achieves linear time complexity and high adaptability.
Fast algorithm for analyzing huge social networks.
problem Analyzing dynamic social networks with large numbers of actors.
method Hierarchical strategy for latent space inference with spline processes and machine learning optimization.
result Can fit millions of nodes in a few minutes.
VED framework learns low-dimensional latent representations of physical systems.
problem Learning latent representations of complex physical systems.
method Variational Encoder-Decoder (VED) framework with KL divergence and covariance regularization.
result VED achieves lower-dimensional latent representations with improved feature disentanglement.
NegBio-VAE models neural spike counts with negative binomial distribution.
problem Limited biological plausibility of continuous latent variables in VAEs for neural spike modeling.
method Proposes a negative binomial latent-variable model with a dispersion parameter for overdispersed spike count modeling.
result NegBio-VAE outperforms competing models in reconstruction and generation tasks.
Improved GANs model geological facies with diversity and unbiased distribution.
problem Generating unbiased and representative geological models from training images.
method Info-WGAN combining InfoGAN, Wasserstein distance, and Gradient Penalty.
result Generated samples have equal probability distribution as training data.
Generalizes bits back coding for time-series models with latent Markov structures.
problem Efficiently compressing time-series data with latent Markov structures.
method Extends bits back coding to time-series models with latent Markov structures, including HMMs and LGSSMs.
result Effective for small scale models, promising for larger scale settings like video compression.
A method to improve image synthesis diversity using mutual information.
problem Mode collapse in conditional GANs for multimodal image synthesis.
method Explicitly estimate and maximize mutual information between latent code and output image.
result Prevents mode collapse and encourages synthesis of diverse images.
DD-VAE uses deterministic decoding for better latent code utilization in discrete data.
problem Inflexible decoders in VAEs lead to poor utilization of latent codes in discrete data.
method Proposed DD-VAE with deterministic decoding and new proposal distributions.
result DD-VAE improves latent code utilization and structure of learned manifold.
We consider the problem of training generative models with deep neural networks as generators, i.e. to map latent codes to data points. Whereas the dominant paradigm combines simple priors over codes with complex deterministic models, we propose instead to use more flexible code distributions. These distributions are e…
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.
A new approach predicts next observations without explicit decoding for better control.
problem High-dimensional observations and unknown dynamics in real-world control tasks.
method Proposes a novel information-theoretic LCE approach using predictive coding to develop a decoder-free model.
result The model reliably learns a controllable latent space leading to superior performance.
A new method learns manifold-valued latents without an encoder.
problem Distorting data with intrinsic non-Euclidean structure.
method Riemannian generative decoder that learns latents directly.
result Learned representations respect the prescribed geometry and capture intrinsic non-Euclidean structure.
p3VAE combines physics and machine learning for robust data representations.
problem Improving machine learning models' robustness to environmental factors of variation.
method Physics-informed variational autoencoder integrating physical knowledge with neural networks.
result p3VAE outperforms competing models in extrapolation and interpretability. We create interpretable word embeddings through sparse coding.
problem Difficult to interpret word embeddings in natural language processing.
method Transform pretrained dense word embeddings into sparse embeddings through sparse coding.
result Sparse embeddings are more interpretable and achieve good performance.