.png){kind=icon}
.png){kind=icon}
Return
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}
Share.png){kind=icon}
Save
Abstract
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/ )
Keywords:
GCNNs
Graph construction
Graph datasets
Graph classification
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W