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.
Disentangled generative models map a latent code vector to a target space, while enforcing that a subset of the learned latent codes are interpretable and associated with distinct properties of the target distribution. Recent advances have been dominated by Variational AutoEncoder (VAE)-based methods, while training di…
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.
Quantizes latent space to improve disentanglement in models.
problem Learning disentangled representations from unlabeled data.
method Quantizes latent space into discrete code vectors with a learnable scalar codebook and applies high weight decay regularization.
result Quantized-latent autoencoder (QLAE) outperforms prior work in disentanglement without sacrificing data reconstruction.
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.
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.
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.
Unsupervised mesh disentanglement separates identity and pose.
problem Geometric disentanglement for 3D deformable models.
method CFAN-VAE architecture using conformal factor and normal features.
result CFAN-VAE achieves state-of-the-art performance on unsupervised geometric disentanglement.
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.
We address the problem of unsupervised disentanglement of latent representations learnt via deep generative models. In contrast to current approaches that operate on the evidence lower bound (ELBO), we argue that statistical independence in the latent space of VAEs can be enforced in a principled hierarchical Bayesian …
Improved disentanglement through learned feature aggregation.
problem Disentangling latent factors in images.
method Variational autoencoder trained on regionally aggregated feature maps from ImageNet.
result 2nd place in NeurIPS 2019 disentanglement challenge.
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.
New framework TDRL identifies latent causal variables from sequential data.
problem Identify latent causal variables from sequential data.
method Proposes TDRL framework to recover time-delayed latent causal variables and identify their relations from measured sequential data.
result Identifies latent causal variables reliably from sequential data.
The notion of disentangled autoencoders was proposed as an extension to the variational autoencoder by introducing a disentanglement parameter β, controlling the learning pressure put on the possible underlying latent representations. For certain values of β this kind of autoencoders is capable of encoding independ…
We address the problem of severe class imbalance in unsupervised domain adaptation, when the class spaces in source and target domains diverge considerably. Till recently, domain adaptation methods assumed the aligned class spaces, such that reducing distribution divergence makes the transfer between domains easier. Su…
We present new intuitions and theoretical assessments of the emergence of disentangled representation in variational autoencoders. Taking a rate-distortion theory perspective, we show the circumstances under which representations aligned with the underlying generative factors of variation of data emerge when optimising…
This work proposes a model to disentangle image factors effectively and control their manipulation.
problem Controlling disentanglement during image editing while preserving object identity.
method Encoder-decoder architecture with decorrelation regularization and soft target representations.
result The model successfully disentangles image factors and manipulates them effectively.
This paper tackles disentanglement in image editing and reconstruction.
problem Learning disentangled image representations and balancing disentanglement strength and reconstruction quality.
method Distance covariance based decorrelation regularization for disentanglement, soft target representation for reconstruction, and collapsing AE decoder and GAN generator.
result The proposed model improves the disentanglement strength and perceptual quality of generated images.
Improved clustering accuracy with disentangled latent code representation.
problem Improving k-Means clustering performance.
method Optimizing the entanglement of autoencoder latent code representation using soft nearest neighbor loss with annealing temperature.
result 96.2% test clustering accuracy on MNIST, 85.6% on Fashion-MNIST, and 79.2% on EMNIST Balanced datasets.
GCAE uses density estimation to achieve reliable disentanglement in latent space.
problem Disentangled learning representations suffer from reliability issues.
method GCAE uses Gaussian Channel Autoencoder with Dual Total Correlation (DTC) to avoid the curse of dimensionality.
result GCAE achieves highly competitive and reliable disentanglement scores.
We address the problem of unsupervised disentanglement of discrete and continuous explanatory factors of data. We first show a simple procedure for minimizing the total correlation of the continuous latent variables without having to use a discriminator network or perform importance sampling, via cascading the informat…
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.
DIVE learns video representations even with missing data.
problem Missing data in video sequences.
method Disentangled Imputed Video autoEncoder (DIVE) with missingness latent variable.
result DIVE outperforms state-of-the-art baselines in imputing and predicting missing video frames.
New principle for disentangling latent factors using sparse regularization.
problem Disentangling latent factors from complex data.
method Sparse regularization of latent mechanisms to induce disentanglement.
result Recovery of latent variables up to permutation under certain conditions.
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.
Disentangled representations, where the higher level data generative factors are reflected in disjoint latent dimensions, offer several benefits such as ease of deriving invariant representations, transferability to other tasks, interpretability, etc. We consider the problem of unsupervised learning of disentangled rep…
Unified framework for disentangled representations using mechanistic independence.
problem Identifiability of disentangled latent factors under statistical dependencies.
method Introduces mechanistic independence to characterize latent factors by their actions on observed variables, proposing various independence criteria.
result Establishes conditions for identifiability of latent subspaces without statistical assumptions.
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.
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.
The paper tackles causal disentanglement with linear models and interventions.
problem Identify latent variables in a causal model from observed data.
method Use linear transformations and interventions to uniquely identify latent variables.
result A single intervention on each latent variable is sufficient for identifying the latent causal model.
A new method uses hyperspherical latent spaces to disentangle data with periodic structures.
problem Disentangling data with periodic or cyclic underlying factors in Euclidean space.
method Diffusion Variational Autoencoder with a modified Evidence Lower Bound.
result The method can recover periodic true factors effectively.
New method learns disentangled discrete representations using categorical variational autoencoders.
problem Learning disentangled representations from discrete latent spaces.
method Replaced standard Gaussian VAE with a categorical VAE to mitigate rotational invariance.
result Categorical distributions improve learning of disentangled representations.
New method for disentangling latent factors with sparse dependencies.
problem Disentangling latent factors from observed variables and past factors.
method Mechanism sparsity regularization and sparse causal graphical model.
result Identifiability of latent factors up to a sparse causal graph.
DGA and DVGA learn disentangled graph representations to improve graph analysis.
problem Holistic graph auto-encoders fail to capture latent factors effectively.
method Design disentangled graph convolutional network and component-wise flow, impose independence constraints.
result Improved disentangled graph representations enhance graph analysis tasks.
New findings show disentangled latent representations are not enough for robust compositional generalization.
problem Deep learning models struggle with compositional generalization, especially in out-of-distribution samples.
method Investigated a 2D Gaussian generation task with fully disentangled inputs, then forced disentangled latent representations into full-dimensional output space.
result Forcing disentangled latent representations into full-dimensional output space enables robust compositional generalization.
Method ranks generative models without needing latent factor supervision.
problem Challenges in selecting generative models for qualities like disentanglement.
method Ranking generative models based on training dynamics, without requiring labels for latent factors.
result Method correlates with supervised disentanglement metrics and can predict downstream performance.
q-VAE extracts disentangled latent spaces for robot control and dynamic systems.
problem Disentangled representation learning for latent spaces in robotics.
method Proposes q-VAE based on Tsallis statistics, improving disentanglement and latent dynamics.
result Improves disentangled representation while maintaining data reconstruction accuracy.
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…
Study shows disentanglement models learn correlations from data, impacting fairness.
problem Disentanglement models learn correlations in real-world data, affecting downstream applications.
method Empirical study on 4260 models, analyzing correlations in latent representations.
result Systematically induced correlations are learned by disentanglement models, impacting fairness.
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.
Here we propose a novel model family with the objective of learning to disentangle the factors of variation in data. Our approach is based on the spike-and-slab restricted Boltzmann machine which we generalize to include higher-order interactions among multiple latent variables. Seen from a generative perspective, the …
A new method for disentangling action sequences improves model stability.
problem Challenges in unsupervised disentanglement learning due to incomplete theories and abstract notions.
method Introducing disentangling action sequences and a novel fractional variational autoencoder (FVAE) framework.
result FVAE improves the stability of disentanglement for action sequences.
A novel disentangled graph autoencoder improves treatment effect estimation from networked observational data.
problem Treatment effect estimation from observational data is challenging due to unconfoundedness assumption and latent confounders.
method Proposes a disentangled variational graph autoencoder to disentangle latent factors and enforce factor independence.
result Extensive experiments show superior performance compared to state-of-the-art approaches.
We present a framework for learning disentangled and interpretable jointly continuous and discrete representations in an unsupervised manner. By augmenting the continuous latent distribution of variational autoencoders with a relaxed discrete distribution and controlling the amount of information encoded in each latent…
We address the problem of disentangled representation learning with independent latent factors in graph convolutional networks (GCNs). The current methods usually learn node representation by describing its neighborhood as a perceptual whole in a holistic manner while ignoring the entanglement of the latent factors. Ho…
We develop a generalisation of disentanglement in VAEs---decomposition of the latent representation---characterising it as the fulfilment of two factors: a) the latent encodings of the data having an appropriate level of overlap, and b) the aggregate encoding of the data conforming to a desired structure, represented t…
New insights explain why β-VAEs fail at disentanglement.
problem Disentanglement performance of β-VAEs peaks at intermediate β and collapses as regularization increases. method Formalized information-theoretic mechanism, introduced λβ-VAE to stabilize disentanglement. result Strong regularization pressure leads to mutual information collapse in β-VAEs. We propose a family of novel hierarchical Bayesian deep auto-encoder models capable of identifying disentangled factors of variability in data. While many recent attempts at factor disentanglement have focused on sophisticated learning objectives within the VAE framework, their choice of a standard normal as the latent…