.png){kind=icon}
返回
Graph classification via discriminative edge feature learning
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2023.109799.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Spectral graph convolutional neural networks (GCNNs) have been producing encouraging results in graph classification tasks. However, most spectral GCNNs utilize fixed graphs when aggregating node features while omitting edge feature learning and failing to get an optimal graph structure. Moreover, many ex-isting graph datasets do not provide initialized edge features, further restraining the ability of learning edge features via spectral GCNNs. In this paper, we try to address this issue by designing an edge fea-ture scheme and an add-on layer between every two stacked graph convolution layers in spectral GCNN. Both are lightweight while effective in filling the gap between edge feature learning and performance enhancement of graph classification. The edge feature scheme makes edge features adapt to node repre-sentations at different spectral graph convolution layers. The add-on layer helps adjust the edge features to an optimal graph structure. To test the effectiveness of our method, we take Euclidean positions as initial node features and extract graphs with semantic information from point cloud objects. The node features of our extracted graphs are more scalable for edge feature learning than most existing graph datasets (in one-hot encoded label format). Three new graph datasets are constructed based on Model-Net40, ModelNet10 and ShapeNet Part datasets. Experimental results show that our method outperforms state-of-the-art graph classification methods on the new datasets. Our code and the constructed graph datasets will be released to the community.& COPY; 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ )
Keyword:
GCNNs
Graph construction
Graph datasets
Graph classification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
分享收藏Every node counts: Self-ensembling graph convolutional networks for semi-supervised learning.png)
PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Input-to-state stability of impulsive reaction-diffusion neural networks with infinite distributed delays具有无限分布时滞的脉冲反应扩散神经网络的输入-状态稳定性
PREAI
分享收藏Robust Kalman filtering for nonlinear multivariable stochastic systems in the presence of non-Gaussian noise存在非高斯噪声的非线性多变量随机系统的鲁棒卡尔曼滤波
PREAI
分享收藏分享收藏SEGREGATION OF GENES DETERMINING RED CELL ANTIGENS AT HIGH LEVELS OF INBREEDING IN CHICKENSGenetics
OAAI
GeneticsIF0
OAAI分享收藏分享收藏
查看更多内容