On-device research index

arXiv research

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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “Cross Convolution”

Cross-GCN: Enhancing Graph Convolutional Network with

k

-Order Feature Interactionscs.LG

Cross-GCN models cross features in GCN for better performance.

problem GCN's lack of cross feature modeling limits its effectiveness.

method Introduces Cross-feature Graph Convolution (Cross-GCN) to model cross features explicitly.

result Explicit cross feature modeling improves GCN's performance on tasks requiring cross features.

Graph Convolutional Network Cross-feature Modeling Feature Interactions Neural Networks Graph Data

2020-03-05abs ↗pdf ↗

JSCN: Joint Spectral Convolutional Network for Cross Domain Recommendationcs.LG

JSCN improves cross-domain recommendation by learning domain-invariant user representations.

problem Cross-domain recommendation data sparsity and domain-incompatibility issues.

method JSCN uses multi-layer spectral convolutions on different graphs to learn domain-invariant user representations and domain adaptive user mappings.

result Significant improvement in cross-domain recommendation performance (9.2% recall, 36.4% MAP improvements).

cross-domain recommendation spectral convolution user representation domain adaptation recommendation systems

2019-10-18abs ↗pdf ↗

Handwritten Chinese Character Recognition by Convolutional Neural Network and Similarity Rankingcs.LG

Improved CNN for HCCR with new loss function and ranking method.

problem Loss of inter-class information in traditional CNN models for HCCR.

method Combining cross entropy with a new similarity ranking function (Average variance similarity) as loss function.

result New loss function (SoftMax cross entropy with Average variance similarity) achieves highest accuracy in HCCR.

Convolutional Neural Networks Chinese Character Recognition Loss Functions Similarity Ranking Cross Entropy

2019-08-30abs ↗pdf ↗

Multitask Gaussian Process with Hierarchical Latent Interactionscs.LG

Enhances MTGP for better hierarchical latent interactions.

problem Current MTGPs struggle with hierarchical latent interactions.

method Proposes a novel kernel representation for hierarchical interactions in LMC of MTGP.

result Promotes knowledge transferring in MTGP through hierarchical interactions.

Multitask Gaussian Process Hierarchical Latent Interactions Kernel Representation Cross Convolution Cross Coregionalization

2018-08-03abs ↗pdf ↗

Data thinning for convolution-closed distributionsstat.ME

Data thinning splits observations into independent parts for convolution-closed distributions.

problem Validation of unsupervised learning results in settings with limited data.

method Data thinning, splitting observations into independent parts following the same distribution.

result Data thinning provides an attractive alternative to cross-validation in settings with limited sample splitting.

data thinning convolution-closed distributions unsupervised learning validation cross-validation

2023-01-18abs ↗pdf ↗

Multi-Graph Convolutional Network for Relationship-Driven Stock Movement Predictionq-fin.ST

Predict stock movement by considering cross effects among stocks.

problem Challenges in predicting stock price movement due to cross effects among stocks.

method Multi-GCGRU framework combining GCN and GRU, encoding cross effects from financial domain knowledge and data-driven relationships.

result Our model outperforms other baselines in predicting stock movement.

stock prediction cross effects deep learning graph convolutional network gated recurrent unit

2020-05-11abs ↗pdf ↗

Deep Scale-spaces: Equivariance Over Scalecs.LG

DSS networks use scale-equivariant cross-correlations to improve image recognition.

problem Improving image recognition by exploiting scale invariance.

method Constructing scale-equivariant cross-correlations based on scale-spaces and semigroups.

result Demonstrated utility on Patch Camelyon and Cityscapes datasets.

scale equivariance deep learning image recognition scale-spaces semigroups

2019-05-28abs ↗pdf ↗

TimeCNN: Refining Cross-Variable Interaction on Time Point for Time Series Forecastingcs.LG

TimeCNN improves forecasting by refining cross-variable interactions over time.

problem Multivariate time series forecasting struggles with dynamic and multifaceted cross-variable correlations.

method TimeCNN uses timepoint-independent convolution kernels to capture evolving relationships among variables.

result TimeCNN outperforms state-of-the-art models in real-world datasets with significant computational and speed advantages.

time series forecasting cross-variable interaction convolutional neural networks multivariate time series dynamic correlations

2024-10-07abs ↗pdf ↗

Multi-Output Convolution Spectral Mixture for Gaussian Processescs.LG

A new kernel for multi-output Gaussian processes reduces undesirable scale effects.

problem Predicting multiple output variables simultaneously with Gaussian processes.

method Design a new kernel (MOCSM) using convolution in the spectral domain to model cross channel dependencies.

result MOCSM kernel reduces undesirable scale effects compared to the Multi-Output Spectral Mixture kernel.

Gaussian processes multi-output spectral mixture convolution kernel design

2018-08-07abs ↗pdf ↗

Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolutioncs.LG

AdaGCN transfers labels across networks via adversarial domain adaptation and graph convolution.

problem Cross-network node classification with limited labeled data.

method Adversarial domain adaptation and graph convolution.

result AdaGCN successfully transfers labels with low labeled data on source networks and significant domain divergence.

graph transfer learning adversarial domain adaptation graph convolution cross-network node classification domain adaptation

2019-09-04abs ↗pdf ↗

A Modified AUC for Training Convolutional Neural Networks: Taking Confidence into Accountcs.LG

Modified AUC improves CNN training by considering model confidence.

problem Improving binary classifier performance metrics.

method Proposes a modified AUC metric that incorporates model confidence into BCE loss for CNN training.

result Demonstrates improved performance on three datasets: MNIST, prostate MRI, and brain MRI.

Convolutional Neural Networks AUC Binary Cross Entropy ROC curve Model Confidence

2020-06-08abs ↗pdf ↗

Automatic Inference of Cross-modal Connection Topologies for X-CNNscs.LG

This paper introduces a way to learn cross-modal convolutional neural network (X-CNN) architectures from a base convolutional network (CNN) and the training data to reduce the design cost and enable applying cross-modal networks in sparse data environments. Two approaches for building X-CNNs are presented. The base app…

2018-05-02abs ↗pdf ↗

A unifying mutual information view of metric learning: cross-entropy vs. pairwise lossescs.LG

Cross-entropy loss linked to metric learning, outperforming complex pairwise losses.

problem Improving metric learning performance without complex optimization schemes.

method Theoretical analysis linking cross-entropy to pairwise losses, showing cross-entropy as an upper bound and equivalent to mutual information maximization.

result Minimizing cross-entropy is equivalent to maximizing mutual information, leading to state-of-the-art performance.

metric learning cross-entropy pairwise losses mutual information optimization

2020-03-19abs ↗pdf ↗

A Bayesian Perspective of Convolutional Neural Networks through a Deconvolutional Generative Modelcs.CV

Designs a new generative model for images using CNNs and improves generalization and performance.

problem Improving image generation and generalization in CNNs.

method Deconvolutional Generative Model (DGM) using a conjugate prior and Rendering Path Normalization (RPN).

result Improves generalization and performance in semi-supervised and supervised learning tasks.

Convolutional Neural Networks Generative Models Bayesian Inference Rendering Path Normalization Max-Min Cross Entropy

2018-11-01abs ↗pdf ↗

Deep Learning for Cross-Border Transaction Anomaly Detection in Anti-Money Laundering Systemscs.LG

This paper uses deep learning to detect money laundering in cross-border transactions.

problem Detecting money laundering in cross-border transactions is challenging due to complexity and scale.

method Unsupervised learning models, including CNNs and hybrid CNNGRU architectures, were tested for anomaly detection.

result Hybrid Convolutional-Recurrent Neural Integration Model (CRNIM) showed superior performance.

money laundering cross-border transactions deep learning unsupervised learning anomaly detection

2024-11-21abs ↗pdf ↗

Multiscale Self Attentive Convolutions for Vision and Language Modelingcs.LG

Paper proposes multiscale self-attentive convolutions for vision and language.

problem Improving language and vision understanding models using self-attention.

method Developed 1D and 2D Self Attentive Convolutions (SAC), multiscale SAC (MSAC).

result MSAC enhances model performance for vision and language tasks.

self-attention convolution vision language multiscale

2019-12-03abs ↗pdf ↗

Empirics versus RMT in financial cross-correlationsq-fin.ST

In order to pursue the issue of the relation between the financial cross-correlations and the conventional Random Matrix Theory we analyse several characteristics of the stock market correlation matrices like the distribution of eigenvalues, the cross-correlations among signs of the returns, the volatility cross-correl…

2007-11-05abs ↗pdf ↗

Street Crossing Aid Using Light-weight CNNs for the Visually Impairedcs.CV

Mobile app uses CNN to help visually impaired cross streets.

problem Helping visually impaired cross streets safely.

method LytNetV2 deep learning model for pedestrian traffic light detection.

result 96% classification accuracy and 6.15 degree angle error.

visually impaired street crossing deep learning CNN pedestrian detection

2019-09-14abs ↗pdf ↗

Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalizationcs.LG

Graph convolution improves linear separability and generalizes to out-of-distribution data.

problem Improving linear separability in semi-supervised classification.

method Applying graph convolution to mixtures of Gaussians in a stochastic block model.

result Graph convolution extends the linear separability regime by a factor of

1/\sqrt{D}

graph convolution semi-supervised classification linear separability out-of-distribution generalization stochastic block model

2021-02-13abs ↗pdf ↗

Deep Convolutional Neural Networks to Diagnose COVID-19 and other Pneumonia Diseases from Posteroanterior Chest X-Rayseess.IV

Deep CNNs diagnose chest X-rays for COVID-19 and other pneumonia.

problem Diagnosing pneumonia from chest X-rays.

method Training and testing VGG16, VGG19, InceptionResNetV2, InceptionV3, and Xception networks on chest X-rays.

result VGG16 with dropout achieves high accuracy and sensitivity.

deep learning chest X-rays COVID-19 pneumonia diagnosis

2020-05-02abs ↗pdf ↗

X-CNN: Cross-modal Convolutional Neural Networks for Sparse Datasetsstat.ML

In this paper we propose cross-modal convolutional neural networks (X-CNNs), a novel biologically inspired type of CNN architectures, treating gradient descent-specialised CNNs as individual units of processing in a larger-scale network topology, while allowing for unconstrained information flow and/or weight sharing b…

2016-10-01abs ↗pdf ↗

Domain transfer convolutional attribute embeddingcs.LG

In this paper, we study the problem of transfer learning with the attribute data. In the transfer learning problem, we want to leverage the data of the auxiliary and the target domains to build an effective model for the classification problem in the target domain. Meanwhile, the attributes are naturally stable cross d…

2018-03-26abs ↗pdf ↗

Murmur Detection Using Parallel Recurrent & Convolutional Neural Networkscs.SD

Deep neural network detects heart murmur with high accuracy.

problem Detecting heart murmur from heart sound recordings.

method Parallel combination of RNN-BiLSTM and CNN.

result 96-100% sensitivity and specificity, 98% F1 score.

heart murmur deep learning neural networks recurrent neural networks convolutional neural networks

2018-08-13abs ↗pdf ↗

MGCN: Semi-supervised Classification in Multi-layer Graphs with Graph Convolutional Networkscs.LG

MGCN improves multi-layer graph classification using node attributes and relations.

problem Lack of comprehensive multi-layer graph embedding methods considering node attributes and different types of edges.

method Proposes MGCN, a method that combines GCN for multi-layer graphs, incorporating node attributes and both within and between layer relations.

result MGCN outperforms other multi-layer and single-layer methods in semi-supervised node classification tasks.

Graph Convolutional Network Multi-layer Graphs Semi-supervised Classification Node Attributes Cross-layer Edges

2018-11-21abs ↗pdf ↗

MedGCN: Medication recommendation and lab test imputation via graph convolutional networkscs.LG

MedGCN uses graph convolutional networks to recommend medications and estimate lab tests.

problem Automatically recommend medications and estimate lab tests for cost savings and better patient care.

method Integrates heterogeneous graph relations, learns node embeddings with graph convolutional networks, and uses cross regularization for multi-task learning.

result MedGCN outperforms state-of-the-art models in both medication recommendation and lab test imputation on real-world datasets.

Medication recommendation Lab test imputation Graph convolutional networks Heterogeneous graph Cross regularization

2019-03-31abs ↗pdf ↗

The Topology-Overlap Trade-Off in Retinal Arteriole-Venule Segmentationcs.CV

Improved retinal vessel segmentation with topology preservation trade-off.

problem Retinal vessel segmentation accuracy and topology preservation trade-off.

method Topology preserving term in the loss function and orientation score guided convolutional module.

result Model achieves higher topological accuracy at the expense of lower overlap metrics.

retinal vasculature segmentation topology preservation convolutional neural networks anisotropic wavelet

2023-03-31abs ↗pdf ↗

Multi-scale Convolution Aggregation and Stochastic Feature Reuse for DenseNetscs.LG

Enhances DenseNets with multi-scale convolutions and stochastic feature reuse.

problem Overfitting in DenseNets with dense feature reuse.

method Multi-scale Convolution Aggregation module and Stochastic Feature Reuse.

result Significant improvement in model accuracy with fewer parameters.

DenseNets Convolution Aggregation Stochastic Feature Reuse Overfitting CIFAR-10

2018-10-02abs ↗pdf ↗

A Transformer with Interleaved Self-attention and Convolution for Hybrid Acoustic Modelseess.AS

Improved hybrid acoustic model using interleaved self-attention and convolution.

problem Limited application of transformer in hybrid acoustic models.

method Proposed a model structure with interleaved self-attention and 1D convolution.

result Competitive recognition results on Librispeech dataset.

Transformer Hybrid Acoustic Model Self-Attention Convolution Librispeech

2019-10-23abs ↗pdf ↗

Question Answering by Reasoning Across Documents with Graph Convolutional Networkscs.CL

Entity-GCN model answers multi-document questions by reasoning across documents.

problem Answering questions based on multiple documents and cross-document relations.

method Graph Convolutional Networks (GCNs) applied to a graph of mentions and their relations.

result Achieves state-of-the-art results on WikiHop dataset.

Graph Convolutional Networks Multi-document QA Reasoning Across Documents Entity Mention Relations

2018-08-29abs ↗pdf ↗

Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Miningcs.CV

This paper improves image super-resolution by integrating cross-scale non-local attention.

problem Improving image super-resolution by leveraging long-range and cross-scale feature correlations.

method Proposes a Cross-Scale Non-Local (CS-NL) attention module integrated into a recurrent neural network.

result Significantly improved performance on SISR benchmarks.

image super-resolution non-local attention cross-scale feature correlation exhaustive self-exemplars mining

2020-06-02abs ↗pdf ↗

Convolutional capsule network for classification of breast cancer histology imagescs.CV

Automatization of the diagnosis of any kind of disease is of great importance and it's gaining speed as more and more deep learning solutions are applied to different problems. One of such computer aided systems could be a decision support too able to accurately differentiate between different types of breast cancer hi…

2018-04-23abs ↗pdf ↗

DANE: Domain Adaptive Network Embeddingcs.LG

DANE adapts network embeddings across multiple domains.

problem Learning embeddings for multiple networks without transferability.

method Graph Convolutional Network with adversarial learning.

result DANE achieves superior performance in cross-network domain adaptation.

network embedding domain adaptation graph convolutional network adversarial learning cross-network

2019-06-03abs ↗pdf ↗

Step Change Improvement in ADMET Prediction with PotentialNet Deep Featurizationcs.LG

Deep featurization improves ADMET prediction accuracy.

problem Predicting ADMET properties to reduce clinical trial failures.

method Learning features from explicit molecular graphs using graph convolutions.

result Achieved unprecedented accuracy in ADMET property prediction.

ADMET deep featurization molecular prediction graph convolutions cross-validation

2019-03-28abs ↗pdf ↗

Regularizing Semi-supervised Graph Convolutional Networks with a Manifold Smoothness Losscs.LG

The paper introduces a new loss function to prevent overfitting in semi-supervised graph networks.

problem Overfitting in semi-supervised graph networks trained with cross-entropy loss.

method Proposes an unsupervised manifold smoothness loss to regularize the graph convolutional networks.

result Adding the proposed loss consistently improves performance of graph networks.

graph convolutional networks semi-supervised learning overfitting manifold smoothness regularization

2020-02-11abs ↗pdf ↗

Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networksmath.NA

Deep networks, especially convolutional neural networks (CNNs), have been successfully applied in various areas of machine learning as well as to challenging problems in other scientific and engineering fields. This paper introduces Butterfly-Net, a low-complexity CNN with structured and sparse cross-channel connection…

2018-05-18abs ↗pdf ↗

Graph Capsule Convolutional Neural Networksstat.ML

Graph Convolutional Neural Networks (GCNNs) are the most recent exciting advancement in deep learning field and their applications are quickly spreading in multi-cross-domains including bioinformatics, chemoinformatics, social networks, natural language processing and computer vision. In this paper, we expose and tackl…

2018-05-21abs ↗pdf ↗

On-Device Transfer Learning for Personalising Psychological Stress Modelling using a Convolutional Neural Networkcs.LG

Personalized stress model using transfer learning from 20 participants.

problem Limited generalizability of machine learning models due to individual physiological differences.

method Transfer learning from a base model trained on 20 participants' physiological data collected in real-time.

result Improved model personalization and cross-domain performance.

transfer learning personalized stress model convolutional neural network physiological sensors real-time data

2020-04-03abs ↗pdf ↗

Deep brain state classification of MEG datacs.LG

Deep neural nets decode brain tasks from MEG data.

problem Classifying brain states from MEG data.

method Three deep neural network models with attention mechanisms.

result Attention mechanisms improve model generalization.

deep learning neuroimaging MEG brain decoding attention mechanisms

2020-07-02abs ↗pdf ↗

A Dictionary Approach to Domain-Invariant Learning in Deep Networkscs.LG

A new CNN architecture tackles domain shifts with a dictionary approach.

problem Handling domain shifts in deep learning models.

method Decompose CNN layers into domain-specific and shared parts using a dictionary of atoms.

result The approach promotes shared semantics across domains with minimal additional parameters.

domain-invariant learning deep learning CNN dictionary approach domain shifts

2019-09-25abs ↗pdf ↗

Transferability of Operational Status Classification Models Among Different Wind Turbine Typesqstat.ML

Wind turbine status classification models are improved for cross-site applicability.

problem Standard models don't generalize across different wind turbines.

method Data normalization and convolutional neural networks with feature-space extension.

result Trained models successfully classified wind turbines from different sites.

wind turbines status classification transferability supervised learning convolutional neural networks

2019-03-21abs ↗pdf ↗

An Interpretable Generative Framework for Anomaly Detection in High-Dimensional Financial Time Seriesstat.ML

ReGEN-TAD detects anomalies in financial time series with interpretable models.

problem Detecting anomalies in complex financial time series with high-dimensional data.

method Integrates machine learning with econometric diagnostics in a refined convolutional--transformer architecture.

result Unified anomaly score without labeled data, robust to structured deviations.

financial time series anomaly detection interpretable models machine learning econometrics

2026-03-09abs ↗pdf ↗

Cross-Domain Deep Face Matching for Real Banking Security Systemscs.CV

Ensuring the security of transactions is currently one of the major challenges that banking systems deal with. The usage of face for biometric authentication of users is attracting large investments from banks worldwide due to its convenience and acceptability by people, especially in cross-domain scenarios, in which f…

2018-06-20abs ↗pdf ↗

Large-Margin Softmax Loss for Convolutional Neural Networksstat.ML

Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component does not explicitly encourage discriminative learning of features. In this paper, we propose a gene…

2016-12-07abs ↗pdf ↗

Cardiac Arrhythmia Detection from ECG Combining Convolutional and Long Short-Term Memory Networkseess.SP

Objectives: Atrial fibrillation (AF) is a common heart rhythm disorder associated with deadly and debilitating consequences including heart failure, stroke, poor mental health, reduced quality of life and death. Having an automatic system that diagnoses various types of cardiac arrhythmias would assist cardiologists to…

2018-01-30abs ↗pdf ↗

Graph Convolution Networks Using Message Passing and Multi-Source Similarity Features for Predicting circRNA-Disease Associationcs.LG

Graph network predicts circRNA-disease associations using multi-source similarity features.

problem Identifying circRNA-disease associations is challenging and time-consuming.

method Proposes a graph convolution network framework using multi-source similarity information.

result Framework predicts circRNA-disease associations with promising results and outperforms existing methods.

graph convolution networks circRNA disease association multi-source similarity deep learning

2020-09-15abs ↗pdf ↗

A few filters are enough: Convolutional Neural Network for P300 Detectioncs.LG

A simple CNN architecture outperforms complex ones in P300 detection.

problem Efficiently detecting P300 component from EEG signals.

method Used a simple CNN architecture with a single depthwise separable 1D convolutional layer followed by a fully connected Sigmoid neuron.

result A single depthwise separable 1D convolutional layer with four filters achieved competitive performance.

CNN P300 EEG BCI SepConv1D

2019-09-16abs ↗pdf ↗

Attentive cross-modal paratope predictionstat.ML

Antibodies are a critical part of the immune system, having the function of directly neutralising or tagging undesirable objects (the antigens) for future destruction. Being able to predict which amino acids belong to the paratope, the region on the antibody which binds to the antigen, can facilitate antibody design an…

2018-06-12abs ↗pdf ↗

Scaling Limits of Bivariate Nearly-Unstable Hawkes Processes and Applications to Rough Volatilitymath.PR

Study of coupled Hawkes processes with rough-volatility limits.

problem Understanding coupled Hawkes processes with rough-volatility limits.

method Proving weak convergence of rescaled intensity vector to stochastic Volterra equations.

result Limiting components exhibit different degrees of roughness and cross-decorrelation law.

Hawkes processes rough volatility coupled systems weak convergence Volterra equations

2026-05-05abs ↗pdf ↗