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.
Improved VAE learns disentangled representations with less supervision.
Class labels are often imperfectly observed, due to mistakes and to genuine ambiguity among classes. We propose a new semi-supervised deep generative model that explicitly models noisy labels, called the Mislabeled VAE (M-VAE). The M-VAE can perform better than existing deep generative models which do not account for l…
CVAE learns disentangled and coupled representations without prior knowledge.
Variational autoencoders (VAEs), as well as other generative models, have been shown to be efficient and accurate for capturing the latent structure of vast amounts of complex high-dimensional data. However, existing VAEs can still not directly handle data that are heterogenous (mixed continuous and discrete) or incomp…
Proposes a supervised VAE to reveal model invariances for interpretability.
Semi-supervised learning is sought for leveraging the unlabelled data when labelled data is difficult or expensive to acquire. Deep generative models (e.g., Variational Autoencoder (VAE)) and semisupervised Generative Adversarial Networks (GANs) have recently shown promising performance in semi-supervised classificatio…
WeLa-VAE learns interpretable disentangled representations with weak supervision.
Automates galaxy morphology classification with less human labelling.
Proposes a new VAE framework for anomaly detection in time series data.
JRFs improve semi-supervised learning by balancing generation and classification.
Study shows how to manipulate VAEs for attacks and assess their robustness.
Improved disentanglement of data factors using recursive training.
We present a new flavor of Variational Autoencoder (VAE) that interpolates seamlessly between unsupervised, semi-supervised and fully supervised learning domains. We show that unlabeled datapoints not only boost unsupervised tasks, but also the classification performance. Vice versa, every label not only improves class…
Self-supervised VAEs improve data compression and generation.
We extend Stochastic Gradient Variational Bayes to perform posterior inference for the weights of Stick-Breaking processes. This development allows us to define a Stick-Breaking Variational Autoencoder (SB-VAE), a Bayesian nonparametric version of the variational autoencoder that has a latent representation with stocha…
Proposes deep quantile regression for uncertainty estimation in lesion detection.
Extracting large amounts of data from biological samples is not feasible due to radiation issues, and image processing in the small-data regime is one of the critical challenges when working with a limited amount of data. In this work, we applied an existing algorithm named Variational Auto Encoder (VAE) that pre-train…
CCVAE captures label characteristics in VAEs for better representation learning.
New hashing method improves document retrieval precision.
Predicting smartphone users location with WiFi fingerprints has been a popular research topic recently. In this work, we propose two novel deep learning-based models, the convolutional mixture density recurrent neural network and the VAE-based semi-supervised learning model. The convolutional mixture density recurrent …
A new VAE model improves disentanglement with identifiable latent factors.
For a robot to perform complex manipulation tasks, it is necessary for it to have a good grasping ability. However, vision based robotic grasp detection is hindered by the unavailability of sufficient labelled data. Furthermore, the application of semi-supervised learning techniques to grasp detection is under-explored…
SOS-VAE improves generative models for scientific applications by correcting decoder bias.
Improved VAE representations lead to better image classification.
In the field of machine learning, it is still a critical issue to identify and supervise the learned representation without manually intervening or intuition assistance to extract useful knowledge or serve for the downstream tasks. In this work, we focus on supervising the influential factors extracted by the variation…
A new Multi-Stream VAE separates multiple sources in images and audio.
This paper characterizes VAE training pathologies and their effects on tasks.
New method for one-shot timbre transfer in music.
Proposes a VAE with Student- mixture model for authorship attribution.
New technique learns causally disentangled representations for better generation.
EXoN creates an explainable latent space for semi-supervised learning.
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…
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…
The paper investigates instance-based interpretation methods for VAEs.
Optimizes VAE hyperparameters for efficient training and manifold discovery.
This work analyzes VQ-VAEs using information theory, focusing on latent variables and their impact on generalization and data generation.
In anomaly detection (AD), one seeks to identify whether a test sample is abnormal, given a data set of normal samples. A recent and promising approach to AD relies on deep generative models, such as variational autoencoders (VAEs), for unsupervised learning of the normal data distribution. In semi-supervised AD (SSAD)…
New methods improve feature extraction and representation quality in supervised and unsupervised DR.
The unsupervised training of GANs and VAEs has enabled them to generate realistic images mimicking real-world distributions and perform image-based unsupervised clustering or semi-supervised classification. Combining the power of these two generative models, we introduce Multi-Adversarial Variational autoEncoder Networ…
We present two deep generative models based on Variational Autoencoders to improve the accuracy of drug response prediction. Our models, Perturbation Variational Autoencoder and its semi-supervised extension, Drug Response Variational Autoencoder (Dr.VAE), learn latent representation of the underlying gene states befor…
VAE fails to encode typical samples, new method improves robustness.
Learning interpretable representations of data remains a central challenge in deep learning. When training a deep generative model, the observed data are often associated with certain categorical labels, and, in parallel with learning to regenerate data and simulate new data, learning an interpretable representation of…
This paper proposes Dirichlet Variational Autoencoder (DirVAE) using a Dirichlet prior for a continuous latent variable that exhibits the characteristic of the categorical probabilities. To infer the parameters of DirVAE, we utilize the stochastic gradient method by approximating the Gamma distribution, which is a comp…
New JSA autoencoders tackle discrete latent variable models for semi-supervised learning.
Direct optimization of binary latent VAEs achieves competitive results without sampling.
HH-VAEM improves imputation and acquisition of missing data using hierarchical models and Hamiltonian Monte Carlo.
Given the emerging global threat of antimicrobial resistance, new methods for next-generation antimicrobial design are urgently needed. We report a peptide generation framework PepCVAE, based on a semi-supervised variational autoencoder (VAE) model, for designing novel antimicrobial peptide (AMP) sequences. Our model l…
Study shows bottlenecks improve image segmentation quality.