Structure-Aware Multi-Hop Graph Convolution for Graph Neural Networks
Not on the map. Why?
Abstract (arXiv)
In this paper, we propose a spatial graph convolution (GC) to classify signals on a graph. Existing GC methods are limited to using the structural information in the feature space. Additionally, the single step of GCs only uses features on the one-hop neighboring nodes from the target node. In this paper, we propose two methods to improve the performance of GCs: 1) Utilizing structural information in the feature space, and 2) exploiting the multi-hop information in one GC step. In the first method, we define three structural features in the feature space: feature angle, feature distance, and relational embedding. The second method aggregates the node-wise features of multi-hop neighbors in a GC. Both methods can be simultaneously used. We also propose graph neural networks (GNNs) integrating the proposed GC for classifying nodes in 3D point clouds and citation networks. In experiments, the proposed GNNs exhibited a higher classification accuracy than existing methods.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 31 of its 48 references that are in the map. First posted on arXiv 3 Dec 2021.
Builds on
31 of 48 references.
References · 31
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
- 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
- 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
- 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
- 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
- 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
19 more
- 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
- 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
- 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
- 2019Graph U-Netscited by 489
- 2017Representation Learning on Graphs: Methods and Applicationscited by 456
- 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
- 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
- 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
- 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
- 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
- 2019Interpolated Convolutional Networks for 3D Point Cloud Understandingcited by 86
- 2018Local Spectral Graph Convolution for Point Set Feature Learningcited by 84
- 2018RGCNN: Regularized Graph CNN for Point Cloud Segmentationcited by 70
- 2019A-CNN: Annularly Convolutional Neural Networks on Point Cloudscited by 66
- 2019ConvPoint: Continuous Convolutions for Point Cloud Processingcited by 62
- 2018A Graph-CNN for 3D Point Cloud Classificationcited by 49
- 2018Graph Spectral Image Processingcited by 41
- 2019Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Featurescited by 31
- 20183DTI-Net: Learn Inner Transform Invariant 3D Geometry Features using Dynamic GCNcited by 7
Built on by
Citing papers per year: 2023: 1.
1 paper.