Beyond topology-driven graph convolution: Node patch convolutional network for node representation learning
Authors:
- Jinsong ChenJCJinsong Chen
- Mingwen TongMTMingwen Tong
- Hao FanHFHao Fan
- Yuxin TanYTYuxin Tan
- Duantengchuan LiDuantengchuan Li
- 8 October 2026
- journal article
- Published by Elsevier in Pattern Recognition
- Vol. 183
Abstract
No abstract availableFunding Information
- Natural Science Foundation of Hubei Province (2025AFB294)
- Natural Science Foundation of Hubei Province (2026AFB619)
- National Natural Science Foundation of China (72474160)
- National Natural Science Foundation of China (62507035)
- National Natural Science Foundation of China (82500221)
This publication has 24 references indexed in Scilit:
- Convolution-aware multi-view graph contrastive learningPattern Recognition, 2026
- SASA: Bridging the semantic gap for node classification in text-attributed graphs using self-adversarial alignmentPattern Recognition, 2026
- FedDCL: Federated diffusion-enhanced contrastive learning for graph anomaly detectionInformation Fusion, 2026
- FastGRAIL: Anchor-graph-based fast adaptive partial multi-label learning with label correlationsPattern Recognition, 2026
- Deep-shallow semantic fusion inference based on graph neural networkInformation Fusion, 2025
- Improving the representational power of graph neural networks via mixed substructure learningInformation Fusion, 2025
- Hybrid long-range dependency-aware graph convolutional network for node classificationKnowledge and Information Systems, 2025
- NAGphormer+: A Tokenized Graph Transformer With Neighborhood Augmentation for Node Classification in Large GraphsIEEE Transactions on Big Data, 2024
- Rethinking the impact of noisy labels in graph classification: A utility and privacy perspectiveNeural Networks, 2024
- PAMT: A Novel Propagation-Based Approach via Adaptive Similarity Mask for Node ClassificationIEEE Transactions on Computational Social Systems, 2024