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.
AEGCN uses autoencoder constraints to improve graph node classification.
Autoencoders compress and reconstruct data for various applications.
Study on dynamics of non-linear autoencoders learning principal components.
In this paper we propose a Deep Autoencoder MIxture Clustering (DAMIC) algorithm based on a mixture of deep autoencoders where each cluster is represented by an autoencoder. A clustering network transforms the data into another space and then selects one of the clusters. Next, the autoencoder associated with this clust…
SidAE combines autoencoders and Siamese networks for self-supervised feature extraction.
The ability of deep neural networks to generalize well in the overparameterized regime has become a subject of significant research interest. We show that overparameterized autoencoders exhibit memorization, a form of inductive bias that constrains the functions learned through the optimization process to concentrate a…
Detects adversarial examples using autoencoders at hidden layers.
Proposes SOMDAGMM for more accurate network intrusion detection.
Spectrum management and resource allocation (RA) problems are challenging and critical in a vast number of research areas such as wireless communications and computer networks. The traditional approaches for solving such problems usually consume time and memory, especially for large size problems. Recently different ma…
Regularization preserves topological data structure in autoencoders.
A new autoencoder architecture captures multiscale data.
Sigmoid autoencoders can implement associative memory with certain conditions.
Batch normalization with regularization turns deterministic autoencoders into generative models.
Feature extraction becomes increasingly important as data grows high dimensional. Autoencoder as a neural network based feature extraction method achieves great success in generating abstract features of high dimensional data. However, it fails to consider the relationships of data samples which may affect experimental…
Network embedding represents nodes in a continuous vector space and preserves structure information from the Network. Existing methods usually adopt a "one-size-fits-all" approach when concerning multi-scale structure information, such as first- and second-order proximity of nodes, ignoring the fact that different scal…
Deep neural network for cancer classification using autoencoders.
A new model for multiview data analysis using graph autoencoders.
Deep clustering has increasingly been demonstrating superiority over conventional shallow clustering algorithms. Deep clustering algorithms usually combine representation learning with deep neural networks to achieve this performance, typically optimizing a clustering and non-clustering loss. In such cases, an autoenco…
AnomalyDAE detects anomalies in networks by learning cross-modality interactions.
Autoencoders identify brain networks linked to stress and genotype.
Variational autoencoders often collapse, showing latent variables are non-identifiable.
This paper introduces structure learning for autoencoder recommenders to improve performance and generalization.
To train an inference network jointly with a deep generative topic model, making it both scalable to big corpora and fast in out-of-sample prediction, we develop Weibull hybrid autoencoding inference (WHAI) for deep latent Dirichlet allocation, which infers posterior samples via a hybrid of stochastic-gradient MCMC and…
The study explores the compressive power of Boolean threshold autoencoders, finding that seven layers are necessary but three are not.
FisherNet extends Autoencoder using Fisher information for better data reconstruction.
Improves latent space structure for better data representation.
This paper explores using SSIM for better image generation in generative models.
The problem of learning a manifold structure on a dataset is framed in terms of a generative model, to which we use ideas behind autoencoders (namely adversarial/Wasserstein autoencoders) to fit deep neural networks. From a machine learning perspective, the resulting structure, an atlas of a manifold, may be viewed as …
Survey of GANs and autoencoders, addressing mode collapse and likelihood issues.
Bidirectional VAE reduces parameters and improves image tasks.
AEGR method improves anomaly detection in autoencoders without needing anomaly-free training data.
Imbalanced data classification problem has always been a popular topic in the field of machine learning research. In order to balance the samples between majority and minority class. Oversampling algorithm is used to synthesize new minority class samples, but it could bring in noise. Pointing to the noise problems, thi…
We introduce the concrete autoencoder, an end-to-end differentiable method for global feature selection, which efficiently identifies a subset of the most informative features and simultaneously learns a neural network to reconstruct the input data from the selected features. Our method is unsupervised, and is based on…
Develops scalable autoencoder for document networks.
New method denoises and fills in missing image data without clean training data.
The problem of estimating event truths from conflicting agent opinions in a social network is investigated. An autoencoder learns the complex relationships between event truths, agent reliabilities and agent observations. A Bayesian network model is proposed to guide the learning process by modeling the relationship of…
End-to-end Sinkhorn Autoencoder reduces data simulation time with noise generation.
There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples. We introduce a simple modification for autoencoder neural networks that yields powerful generative models. Our method masks the autoencoder's parameters to respect autoregressive constraints: ea…
In this paper we study generative modeling via autoencoders while using the elegant geometric properties of the optimal transport (OT) problem and the Wasserstein distances. We introduce Sliced-Wasserstein Autoencoders (SWAE), which are generative models that enable one to shape the distribution of the latent space int…
Any autoencoder network can be turned into a generative model by imposing an arbitrary prior distribution on its hidden code vector. Variational Autoencoder (VAE) [2] uses a KL divergence penalty to impose the prior, whereas Adversarial Autoencoder (AAE) [1] uses {\it generative adversarial networks} GAN [3]. GAN trade…
A novel disentangled graph autoencoder improves treatment effect estimation from networked observational data.
A new deep clustering model learns both clustering and embedding simultaneously.
We demonstrate a new deep learning autoencoder network, trained by a nonnegativity constraint algorithm (NCAE), that learns features which show part-based representation of data. The learning algorithm is based on constraining negative weights. The performance of the algorithm is assessed based on decomposing data into…
Graph regularized autoencoder improves anomaly detection performance.
New methods improve gradient estimation in autoencoders, enhancing generative network performance.
We present a representation learning method that learns features at multiple different levels of scale. Working within the unsupervised framework of denoising autoencoders, we observe that when the input is heavily corrupted during training, the network tends to learn coarse-grained features, whereas when the input is …
Identifying computational mechanisms for memorization and retrieval of data is a long-standing problem at the intersection of machine learning and neuroscience. Our main finding is that standard overparameterized deep neural networks trained using standard optimization methods implement such a mechanism for real-valued…
Gene expression profiles have been widely used to characterize patterns of cellular responses to diseases. As data becomes available, scalable learning toolkits become essential to processing large datasets using deep learning models to model complex biological processes. We present an autoencoder to capture nonlinear …