A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
GCAE uses density estimation to achieve reliable disentanglement in latent space.
Unified framework for disentangled VAEs improves latent space interpretability.
Generative model disentangles dark matter halo properties.
A new method uses hyperspherical latent spaces to disentangle data with periodic structures.
Study improves interpretability in generative models by disentangling latent variables in scientific datasets.
Quantizes latent space to improve disentanglement in models.
q-VAE extracts disentangled latent spaces for robot control and dynamic systems.
UT module refines VAE latent space, improving disentanglement and interpretability.
New method learns disentangled discrete representations using categorical variational autoencoders.
This work provides uncertainty intervals for semantic latent variables in disentangled latent spaces.
New findings show disentangled latent representations are not enough for robust compositional generalization.
This work improves disentanglement in latent space models without sacrificing generation quality.
Unsupervised mesh disentanglement separates identity and pose.
We address tracking and prediction of multiple moving objects in visual data streams as inference and sampling in a disentangled latent state-space model. By encoding objects separately and including explicit position information in the latent state space, we perform tracking via amortized variational Bayesian inferenc…
A new method for disentangled latent spaces in VAEs that can manipulate attributes.
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…
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…
New method flattens decision boundary by targeting shortcut-aligned axes in disentangled latent space.
New principle for disentangling latent factors using sparse regularization.
Proposes GM Score to evaluate GANs considering diversity, disentanglement, and discriminability.
Method evaluates disentanglement in DLVMs, including those not aligned with latent axes.
Learning representations that disentangle the underlying factors of variability in data is an intuitive way to achieve generalization in deep models. In this work, we address the scenario where generative factors present a multimodal distribution due to the existence of class distinction in the data. We propose N-VAE, …
Unsupervised learning of disentangled representations is an open problem in machine learning. The Disentanglement-PyTorch library is developed to facilitate research, implementation, and testing of new variational algorithms. In this modular library, neural architectures, dimensionality of the latent space, and the tra…
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.
We present a simple neural rendering architecture that helps variational autoencoders (VAEs) learn disentangled representations. Instead of the deconvolutional network typically used in the decoder of VAEs, we tile (broadcast) the latent vector across space, concatenate fixed X- and Y-"coordinate" channels, and apply a…
The success of deep learning in medical imaging is mostly achieved at the cost of a large labeled data set. Semi-supervised learning (SSL) provides a promising solution by leveraging the structure of unlabeled data to improve learning from a small set of labeled data. Self-ensembling is a simple approach used in SSL to…
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 …
The vulnerability of deep neural networks to adversarial attacks has been widely demonstrated (e.g., adversarial example attacks). Traditional attacks perform unstructured pixel-wise perturbation to fool the classifier. An alternative approach is to have perturbations in the latent space. However, such perturbations ar…
A new method for VAEs improves latent space disentanglement without violating probability laws.
We propose a novel VAE-based deep auto-encoder model that can learn disentangled latent representations in a fully unsupervised manner, endowed with the ability to identify all meaningful sources of variation and their cardinality. Our model, dubbed Relevance-Factor-VAE, leverages the total correlation (TC) in the late…
We focus on explicitly learning disentangled representation for natural image generation, where the underlying spatial structure and the rendering on the structure can be independently controlled respectively, yet using no tuple supervision. The setting is significant since tuple supervision is costly and sometimes eve…
The paper tackles causal disentanglement with linear models and interventions.
To improve the ability of VAE to disentangle in the latent space, existing works mostly focus on enforcing independence among the learned latent factors. However, the ability of these models to disentangle often decreases as the complexity of the generative factors increases. In this paper, we investigate the little-ex…
In this work we explore the generalization characteristics of unsupervised representation learning by leveraging disentangled VAE's to learn a useful latent space on a set of relational reasoning problems derived from Raven Progressive Matrices. We show that the latent representations, learned by unsupervised training …
AI learns to classify and represent univariate distributions in a 2D latent space.
Recently there has been an increased interest in unsupervised learning of disentangled representations using the Variational Autoencoder (VAE) framework. Most of the existing work has focused largely on modifying the variational cost function to achieve this goal. We first show that these modifications, e.g. beta-VAE, …
New method for disentangling latent factors with sparse dependencies.
In this paper, we learn disentangled representations of timbre and pitch for musical instrument sounds. We adapt a framework based on variational autoencoders with Gaussian mixture latent distributions. Specifically, we use two separate encoders to learn distinct latent spaces for timbre and pitch, which form Gaussian …
DGA and DVGA learn disentangled graph representations to improve graph analysis.
Method ranks generative models without needing latent factor supervision.
New method better identifies irrelevant variables for more accurate treatment effect estimation.
In order to build language technologies for majority of the languages, it is important to leverage the resources available in public domain on the internet - commonly referred to as `Found Data'. However, such data is characterized by the presence of non-standard, non-trivial variations. For instance, speech resources …
Our work improves VAE latent space clustering by enforcing invariant and equivariant learning.
DeepDIVE disentangles input into marginal and conditional distributions for multi-task learning.
Study shows disentanglement models learn correlations from data, impacting fairness.
A generative model with a disentangled representation allows for independent control over different aspects of the output. Learning disentangled representations has been a recent topic of great interest, but it remains poorly understood. We show that even for GANs that do not possess disentangled representations, one c…
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 …