Soft-GNN:towards robust graph neural networks via self-adaptive data utilization  

作　　者：Yao WU Hong HUANG Yu SONG Hai JIN 

机构地区：[1]National Engineering Research Center for Big Data Technology and System,Service Computing Technology and System Lab,Cluster and Grid Computing Lab,School of Computer Science and Technology,Huazhong University of Science and Technology,Wuhan 430074,China [2]College of Information and Communication,National University of Defense Technology,Wuhan 430019,China [3]Department of Computer Science and Operations Research,Universitéde Montréal,Montreal H3C 3J7,Canada

出　　处：《Frontiers of Computer Science》2025年第4期1-12,共12页计算机科学前沿(英文版)

基　　金：supported by the National Natural Science Foundation of China(Grant No.62127808).

摘　　要：Graph neural networks(GNNs)have gained traction and have been applied to various graph-based data analysis tasks due to their high performance.However,a major concern is their robustness,particularly when faced with graph data that has been deliberately or accidentally polluted with noise.This presents a challenge in learning robust GNNs under noisy conditions.To address this issue,we propose a novel framework called Soft-GNN,which mitigates the influence of label noise by adapting the data utilized in training.Our approach employs a dynamic data utilization strategy that estimates adaptive weights based on prediction deviation,local deviation,and global deviation.By better utilizing significant training samples and reducing the impact of label noise through dynamic data selection,GNNs are trained to be more robust.We evaluate the performance,robustness,generality,and complexity of our model on five real-world datasets,and our experimental results demonstrate the superiority of our approach over existing methods.

关 键 词：graph neural networks node classification label noise robustness 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]