• FastGCN

  • Referenced in 9 articles [sw38089]
  • FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling. The graph convolutional networks ... graphs. To relax the requirement of simultaneous availability of test data, we interpret graph convolutions...
  • DropEdge

  • Referenced in 3 articles [sw37753]
  • DropEdge: Towards Deep Graph Convolutional Networks on Node Classification. Over-fitting and over-smoothing ... main obstacles of developing deep Graph Convolutional Networks (GCNs) for node classification. In particular, over ... input features with the increase in network depth. This paper proposes DropEdge, a novel ... certain number of edges from the input graph at each training epoch, acting like...
  • LightGCN

  • Referenced in 2 articles [sw37571]
  • LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation. Graph Convolution Network (GCN) has become ... which is originally designed for graph classification tasks and equipped with many neural network operations...
  • CayleyNets

  • Referenced in 5 articles [sw38090]
  • CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filters. The rise of graph-structured ... social networks, regulatory networks, citation graphs, and functional brain networks, in combination with resounding success ... spectral domain convolutional architecture for deep learning on graphs. The core ingredient of our model...
  • Pixel2Mesh

  • Referenced in 5 articles [sw31205]
  • represents 3D mesh in a graph-based convolutional neural network and produces correct geometry...
  • DeepGCNs

  • Referenced in 2 articles [sw38086]
  • GCNs Go as Deep as CNNs? Convolutional Neural Networks (CNNs) achieve impressive performance ... Euclidean data. To overcome this challenge, Graph Convolutional Networks (GCNs) build graphs to represent ... from CNNs, specifically residual/dense connections and dilated convolutions, and adapting them to GCN architectures. Extensive...
  • MSRGCN

  • Referenced in 1 article [sw42692]
  • Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction. Human motion prediction ... aperiodicity of future poses. Recently, graph convolutional network has been proven to be very effective ... propose a novel Multi-Scale Residual Graph Convolution Network (MSR-GCN) for human pose prediction...
  • GaitGraph

  • Referenced in 1 article [sw42734]
  • GaitGraph: Graph Convolutional Network for Skeleton-Based Gait Recognition. Gait recognition is a promising video ... GaitGraph that combines skeleton poses with Graph Convolutional Network (GCN) to obtain a modern model...
  • CGC-Net

  • Referenced in 1 article [sw39633]
  • Cell Graph Convolutional Network for Grading of Colorectal Cancer Histology Images. Colorectal cancer (CRC) grading ... present a novel cell-graph convolutional neural network (CGC-Net) that converts each large histology ... introduce Adaptive GraphSage, which is a graph convolution technique that combines multi-level features...
  • Pose2Mesh

  • Referenced in 1 article [sw42752]
  • Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human ... propose Pose2Mesh, a novel graph convolutional neural network (GraphCNN)-based system that estimates...
  • RGCNN

  • Referenced in 2 articles [sw36662]
  • images before feeding them into neural networks, which leads to voluminous data and quantization artifacts ... instead propose a regularized graph convolutional neural network (RGCNN) that directly consumes point clouds. Leveraging ... point cloud as signals on graph, and define the convolution over graph by Chebyshev polynomial...
  • JGR-P2O

  • Referenced in 1 article [sw42731]
  • Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from ... plain feature representation learning with local convolutions. In this paper, a novel pixel-wise prediction ... training. Specifically, we first propose a graph convolutional network (GCN) based joint graph reasoning module ... implemented with an efficient 2D fully convolutional network (FCN) backbone and has only about...
  • GraphSAINT

  • Referenced in 1 article [sw37758]
  • Graph Sampling Based Inductive Learning Method. Graph Convolutional Networks (GCNs) are powerful models for learning...
  • paper2repo

  • Referenced in 1 article [sw32544]
  • paper2repo integrates text encoding and constrained graph convolutional networks (GCN) to automatically learn...
  • LightTrack

  • Referenced in 1 article [sw39261]
  • tracking. We also propose a Siamese Graph Convolution Network (SGCN) for human pose matching...
  • SportsCap

  • Referenced in 1 article [sw40782]
  • introduce a multi-stream spatial-temporal Graph Convolutional Network(ST-GCN) to predict the fine...
  • PiNN

  • Referenced in 2 articles [sw30601]
  • Networks of Molecules and Materials. Atomic neural networks (ANNs) constitute a class of machine learning ... PiNN, we implemented an interpretable graph convolutional neural network variant, PiNet, as well...
  • SyncSpecCnn

  • Referenced in 5 articles [sw26163]
  • with images that are 2D grids, shape graphs are irregular and non-isomorphic data structures ... vertex functions on them by convolutional neural networks, we resort to spectral CNN method that ... kernels in the spectral domain spanned by graph laplacian eigenbases. Under this setting, our network ... different graphs. Towards these goals, we introduce a spectral parameterization of dilated convolutional kernels...
  • Chainer Chemistry

  • Referenced in 1 article [sw39646]
  • models (especially GCNN - Graph Convolutional Neural Network) for chemical property prediction...
  • DeepLGP

  • Referenced in 0 articles [sw37448]
  • this study, we present a graph convolutional network (GCN) based method, named DeepLGP, for prioritizing...