ComGRL: Comprehensive Graph Representation Learning From Local to Global Bridged by Mixup
Top Cited Papers
- 3 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 13 (3) , 2839-2852
Abstract
Graph neural networks (GNNs) have demonstrated remarkable effectiveness in various graph representation learning tasks. However, most of existing methods achieve the information extraction by the simple fusion of local and global information, which is a coarse-grained and static way. This may hinder the establishment of a dynamic and collaborative interaction between global and local information, which is crucial for comprehensively understanding graph data. To address this challenge, we propose a novel framework called comprehensive graph representation learning (ComGRL). ComGRL integrates local information into global information to derive powerful representations. It achieves this by implicitly smoothing local information through flexible graph contrastive learning, ensuring reliable representations for subsequent global exploration. Then ComGRL transfers the locally derived representations to a multihead self-attention module, enhancing their discriminative ability by uncovering diverse and rich global correlations. To achieve dynamic transformation between global and local information under self-supervision with pseudo-labels, ComGRL employs a triple sampling strategy to construct mixed node pairs and applies reliable Mixup augmentation across attributes and structure for the main frameworks. This approach broadens the receptive field and facilitates coordination between local and global representation learning, enabling them to reinforce each other. Experimental results across six widely used graph datasets demonstrate that ComGRL achieves excellent performance in node classification tasks. The code could be available at https://github.com/JinluWang1002/ComGRL.Keywords
Funding Information
- National Natural Science Foundation of China (62403043)
- National Natural Science Foundation of China (62441232)
- National Natural Science Foundation of China (62172023)
- Beijing Natural Science Foundation (L257022)
- China Postdoctoral Science Foundation (2025T180467)
This publication has 34 references indexed in Scilit:
- Dual-level noise augmentation for graph clustering with triplet-wise contrastive learningPattern Recognition, 2025
- DGNN: Decoupled Graph Neural Networks With Structural Consistency Between Attribute and Graph Embedding RepresentationsIEEE Transactions on Big Data, 2024
- Federated Graph Augmentation for Semisupervised Node ClassificationIEEE Transactions on Computational Social Systems, 2024
- Graph Convolutional Network with elastic topologyPattern Recognition, 2024
- GraphMixup: Improving Class-Imbalanced Node Classification by Reinforcement Mixup and Self-supervised Context Prediction2023
- An Overview of Advanced Deep Graph Node ClusteringIEEE Transactions on Computational Social Systems, 2023
- Adaptive graph convolutional clustering network with optimal probabilistic graphNeural Networks, 2022
- Robust Graph Convolutional Clustering With Adaptive Graph Learning2022
- Adversarial Label-Flipping Attack and Defense for Graph Neural Networks2020
- Multilayer Perceptron (MLP)2017