A Flexible Diffusion Convolution for Graph Neural Networks

作     者：Zhao, Songwei Yu, Bo Yang, Kang Zhang, Sinuo Hu, Jifeng Jiang, Yuan Yu, Philip S. Chen, Hechang 

作者机构：Jilin Univ Engn Res Ctr Knowledge Driven Human Machine Intell Sch Artificial Intelligence Changchun 130015 Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore Univ Illinois Dept Comp Sci Chicago IL 60607 USA 

出 版 物：《IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING》 (IEEE Trans Knowl Data Eng)

年 卷 期：2025年第37卷第6期

页      面：3118-3131页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Natural Science Foundation of China [62476110, U2341229] NSF [III-2106758, POSE-2346158] National Key R&D Program of China [2021ZD0112500] Key R&D Project of Jilin Province [20240304200SF] International Cooperation Project of Jilin Province [20220402009GH] 

主　　题：Convolution Graph neural networks Smoothing methods Mathematical models Training Data mining Accuracy Symmetric matrices Feature extraction Electronic mail Diffusion convolution flexible graph neural network (GNN) label smoothing 

摘      要：Graph Neural Networks (GNNs) have been gaining more attention due to their excellent performance in modeling various graph-structured data. However, most of the current GNNs only consider fixed-neighbor discrete message-passing, disregarding the importance of the local structure of different nodes and the implicit information between nodes for smoothing features. Previous approaches either focus on adaptive selection for aggregation structures or treat discrete graph convolution as a continuous diffusion process, but none of them comprehensively considered the above issues, significantly limiting the model s performance. To this end, we present a novel approach called Flexible Diffusion Convolution (Flexi-DC), which exploits the neighborhood information of nodes to set a particular continuous diffusion for each node to smooth features. Specifically, Flexi-DC first extracts the local structure knowledge based on the degrees of nodes in the graph data and then injects it into the diffusion convolution module to smooth features. Additionally, we utilize the extracted knowledge to smooth labels. Flexi-DC is an efficient framework that can significantly improve the performance of most GNN architectures. Experimental results demonstrate that Flexi-DC outperforms their vanilla implementations by an average accuracy of 13.24% (GCN), 16.37% (JKNet), and 11.98% (ARMA) on nine graph datasets with different homophily ratios.