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.
New definition of disentanglement for non-independent factors of variation.
New method learns disentangled discrete representations using categorical variational autoencoders.
Gaussian process variational autoencoders improve disentanglement in time series data.
DGA and DVGA learn disentangled graph representations to improve graph analysis.
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…
GCVAE improves disentanglement in VAEs while balancing reconstruction error.
DISCoVeR learns disentangled representations by separating shared and condition-specific factors.
New technique learns causally disentangled representations for better generation.
Improved disentanglement through learned feature aggregation.
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 framework for disentangling class-related and class-independent factors in data.
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…
New method disentangles shared and private latent factors in multimodal data.
PRI-VAE learns disentangled representations by optimizing principle-of-relevant-information.
Learning to disentangle the hidden factors of variations within a set of observations is a key task for artificial intelligence. We present a unified formulation for class and content disentanglement and use it to illustrate the limitations of current methods. We therefore introduce LORD, a novel method based on Latent…
Paper summarizes unsupervised learning challenges for disentangled representations.
A new method uses hyperspherical latent spaces to disentangle data with periodic structures.
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…
This work improves disentanglement in latent space models without sacrificing generation quality.
The notion of disentangled autoencoders was proposed as an extension to the variational autoencoder by introducing a disentanglement parameter , controlling the learning pressure put on the possible underlying latent representations. For certain values of this kind of autoencoders is capable of encoding independ…
New framework for disentangling graph node and edge features.
New metric for disentangling multivariate representations, accounting for more complex entanglements.
Unsupervised learning of disentangled representations involves uncovering of different factors of variations that contribute to the data generation process. Total correlation penalization has been a key component in recent methods towards disentanglement. However, Kullback-Leibler (KL) divergence-based total correlatio…
Disentangled representations have recently been shown to improve fairness, data efficiency and generalisation in simple supervised and reinforcement learning tasks. To extend the benefits of disentangled representations to more complex domains and practical applications, it is important to enable hyperparameter tuning …
DeepDIVE disentangles input into marginal and conditional distributions for multi-task learning.
Proposes a new method for disentangling data representations using topological analysis.
The problem of feature disentanglement has been explored in the literature, for the purpose of image and video processing and text analysis. State-of-the-art methods for disentangling feature representations rely on the presence of many labeled samples. In this work, we present a novel method for disentangling factors …
A new VAE model improves disentanglement with identifiable latent factors.
We decompose the evidence lower bound to show the existence of a term measuring the total correlation between latent variables. We use this to motivate our -TCVAE (Total Correlation Variational Autoencoder), a refinement of the state-of-the-art -VAE objective for learning disentangled representations, requiring n…
A new method for disentangling action sequences improves model stability.
VDA improves disentanglement of latent representations in complex signals.
Improves disentangled representation learning with multi-stage modeling.
We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independent across the dimensions. We show tha…
Method evaluates disentanglement in DLVMs, including those not aligned with latent axes.
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 extracts factors of variation from data without much supervision.
We propose a novel unsupervised generative model that learns to disentangle object identity from other low-level aspects in class-imbalanced data. We first investigate the issues surrounding the assumptions about uniformity made by InfoGAN, and demonstrate its ineffectiveness to properly disentangle object identity in …
WeLa-VAE learns interpretable disentangled representations with weak supervision.
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…
Learning disentangled representations is considered a cornerstone problem in representation learning. Recently, Locatello et al. (2019) demonstrated that unsupervised disentanglement learning without inductive biases is theoretically impossible and that existing inductive biases and unsupervised methods do not allow to…
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…
Discond-VAE separates continuous and discrete factors in data.
We would like to learn a representation of the data which decomposes an observation into factors of variation which we can independently control. Specifically, we want to use minimal supervision to learn a latent representation that reflects the semantics behind a specific grouping of the data, where within a group the…
Deep latent-variable models learn representations of high-dimensional data in an unsupervised manner. A number of recent efforts have focused on learning representations that disentangle statistically independent axes of variation by introducing modifications to the standard objective function. These approaches general…
We propose the factorized action variational autoencoder (FAVAE), a state-of-the-art generative model for learning disentangled and interpretable representations from sequential data via the information bottleneck without supervision. The purpose of disentangled representation learning is to obtain interpretable and tr…
Method separates data into class and style factors using semi-supervised learning.
The paper connects disentanglement to manifold charts and commutativity.
This paper improves disentanglement in VAEs by progressively learning hierarchical representations.