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

19 results for “Graph-CNN”

A Graph-CNN for 3D Point Cloud Classificationcs.CV

Graph-CNN for 3D point cloud classification tackles non-regular graph topology.

problem Classifying 3D point cloud data with non-regular graph topology.

method Developed PointGCN combining localized graph convolutions and graph downsampling.

result Achieves competitive performance on 3D object classification benchmark ModelNet.

Graph-CNN 3D point cloud classification local structure ModelNet

2018-11-28abs ↗pdf ↗

Graph Wavelet Neural Networkcs.LG

GWNN uses graph wavelets for efficient graph CNNs.

problem Spectral graph CNNs' high computational cost and lack of interpretability.

method Graph wavelet transform for efficient graph convolution.

result GWNN significantly outperforms spectral graph CNNs.

graph wavelet graph CNN graph Fourier transform graph semi-supervised classification

2019-04-12abs ↗pdf ↗

When Work Matters: Transforming Classical Network Structures to Graph CNNcs.LG

Numerous pattern recognition applications can be formed as learning from graph-structured data, including social network, protein-interaction network, the world wide web data, knowledge graph, etc. While convolutional neural network (CNN) facilitates great advances in gridded image/video understanding tasks, very limit…

2018-07-07abs ↗pdf ↗

Adaptive Graph Convolutional Neural Networkscs.LG

Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks. Current filters in graph CNNs are built for fixed and shared graph structure. However, for most real data, the graph structures varies in both size and con…

2018-01-10abs ↗pdf ↗

Some New Layer Architectures for Graph CNNcs.LG

New graph CNN layers improve accuracy on graph datasets.

problem Graph data relations are better represented as graphs, not grids.

method Proposed new graph CNN layers for vertex and edge features.

result Improved classification accuracy on graph datasets.

graph CNN graph data convolutional layers pooling layers fully connected layers

2018-10-31abs ↗pdf ↗

Revisiting convolutional neural network on graphs with polynomial approximations of Laplace-Beltrami spectral filteringcs.LG

Paper revisits graph-CNNs using Laplace-Beltrami spectral filters and polynomials.

problem Improving spectral graph convolutional neural networks (graph-CNNs).

method Developed Laplace-Beltrami CNN (LB-CNN) by replacing graph Laplacian with LB operator and approximating spectral filters using Chebyshev, Laguerre, and Hermite polynomials.

result Classification accuracy of LB-CNN is not dependent on the type of polynomials or operators.

spectral graph convolutional neural networks Laplace-Beltrami operator polynomial approximations Alzheimer's Disease Neuroimaging Initiative (ADNI)cortical thickness

2020-10-26abs ↗pdf ↗

Convolutional Neural Network on Semi-Regular Triangulated Meshes and its Application to Brain Image Datacs.LG

A CNN on semi-regular meshes classifies brain diseases from MRI scans.

problem Classifying brain diseases from MRI scans.

method Developed a vertex-based graph CNN for semi-regular triangulated meshes.

result Vertex-based graph CNN outperformed spectral graph CNN in classifying MCI and AD.

Convolutional Neural Networks Triangulated Meshes Brain Imaging Mild Cognitive Impairment Alzheimer's Disease

2019-03-21abs ↗pdf ↗

DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Modelcs.LG

Convolutional neural networks (CNNs) can be applied to graph similarity matching, in which case they are called graph CNNs. Graph CNNs are attracting increasing attention due to their effectiveness and efficiency. However, the existing convolution approaches focus only on regular data forms and require the transfer of …

2017-12-10abs ↗pdf ↗

Dual-Primal Graph Convolutional Networkscs.LG

In recent years, there has been a surge of interest in developing deep learning methods for non-Euclidean structured data such as graphs. In this paper, we propose Dual-Primal Graph CNN, a graph convolutional architecture that alternates convolution-like operations on the graph and its dual. Our approach allows to lear…

2018-06-03abs ↗pdf ↗

Graph-augmented Convolutional Networks on Drug-Drug Interactions Predictioncs.LG

Graph-augmented CNN predicts drug interactions with high accuracy.

problem Predicting drug-drug interactions (DDIs) with high accuracy.

method Combining graph CNN with an attentive pooling network to extract structural relations between drug pairs.

result Desirable performance with ROC 0.988, F1-score 0.956, and AUPR 0.986.

drug interactions graph-augmented CNN attention pooling drug design

2019-12-08abs ↗pdf ↗

Text classification problems via BERT embedding method and graph convolutional neural networkcs.CL

Combines BERT and graph CNN for improved text classification.

problem Text classification problems

method Combining BERT embedding and graph convolutional neural network

result Graph CNN model performs better than classical models combined with BERT

BERT graph convolutional neural network text classification BBC news IMDB

2021-11-30abs ↗pdf ↗

A Non-Negative Factorization approach to node pooling in Graph Convolutional Neural Networkscs.LG

The paper introduces a pooling mechanism for graph CNNs using NMF.

problem Pooling in graph structured data for efficient computation.

method Non-negative matrix factorization for node pooling.

result The pooling mechanism improves graph classification performance.

Graph Convolutional Neural Networks Pooling Non-negative Matrix Factorization Graph Classification Node Embedding

2019-09-07abs ↗pdf ↗

Human-centric Transfer Learning Explanation via Knowledge Graph [Extended Abstract]cs.LG

Two KG-based methods explain transfer learning in CNN and ZSL.

problem Uninterpretable transfer learning for non-ML experts.

method Knowledge Graph-based explanation for transferability and model justification.

result Rich, human-understandable explanations for transfer learning.

Transfer Learning Knowledge Graph CNN Zero-Shot Learning Interpretability

2019-01-20abs ↗pdf ↗

DFNets: Spectral CNNs for Graphs with Feedback-Looped Filterscs.LG

DFNets uses feedback-looped filters for better graph CNN performance.

problem Improving CNN performance on graph structured data.

method DFNets incorporates feedback-looped spectral graph filters.

result DFNets outperforms state-of-the-art methods in document and entity classification tasks.

spectral CNN graph filters feedback-looped graph structured data semi-supervised learning

2019-10-24abs ↗pdf ↗

Robust Deep Graph Based Learning for Binary Classificationcs.LG

Paper proposes a robust deep graph-based classifier for noisy labels.

problem Difficulty in feature learning with noisy training labels.

method Convolutional neural networks with graph Laplacian regularization (GLR).

result Proposed method outperforms state-of-the-art classifiers on noisy datasets.

graph-based learning convolutional neural networks graph Laplacian regularization binary classification noisy labels

2019-12-06abs ↗pdf ↗

DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networksq-bio.BM

Motivation: Drug discovery demands rapid quantification of compound-protein interaction (CPI). However, there is a lack of methods that can predict compound-protein affinity from sequences alone with high applicability, accuracy, and interpretability. Results: We present a seamless integration of domain knowledges and …

2018-06-20abs ↗pdf ↗

Rational Neural Networks for Approximating Jump Discontinuities of Graph Convolution Operatorcs.LG

For node level graph encoding, a recent important state-of-art method is the graph convolutional networks (GCN), which nicely integrate local vertex features and graph topology in the spectral domain. However, current studies suffer from several drawbacks: (1) graph CNNs relies on Chebyshev polynomial approximation whi…

2018-08-30abs ↗pdf ↗

MT-CGCNN: Integrating Crystal Graph Convolutional Neural Network with Multitask Learning for Material Property Predictioncs.LG

Model predicts multiple material properties with reduced error.

problem Limited materials data and lack of universal material descriptors.

method Integrates CGCNN with multi-task learning.

result Reduces test error by up to 8% for correlated properties.

machine learning materials science crystal graph CNN transfer learning multi-task learning

2018-11-14abs ↗pdf ↗

Rich-Item Recommendations for Rich-Users: Exploiting Dynamic and Static Side Informationcs.LG

Develops a deep learning architecture for rich-item recommendations.

problem Rich data structures with multiple entity types and side-information.

method General formulation, multiple graph-CNN based architecture (AL-GCN), ranking metric pAp@k.

result 5-6% points more accurate than production models in real-world applications.

Recommendation systems Deep learning Graph convolution networks Rich data structures Side information

2020-01-28abs ↗pdf ↗