arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.09171cs.LGcs.AI
收藏

ADEdgeDrop:面向鲁棒图神经网络的对抗性边丢弃方法

ADEdgeDrop: Adversarial Edge Dropping for Robust Graph Neural Networks

College of Computer and Data Science, Fuzhou University(福州大学计算机与数据科学学院);Hong Kong Baptist University(香港浸会大学);University of Vienna(维也纳大学)

Zhaoliang Chen, Zhihao Wu, Ylli Sadikaj, Claudia Plant, Hong-Ning Dai, Shiping Wang, Yiu-Ming Cheung, Wenzhong Guo

AI总结:

针对图神经网络因图数据噪声冗余导致鲁棒性差的问题,提出基于对抗边预测器的边丢弃方法ADEdgeDrop,可灵活适配多类GNN骨干,在6个基准数据集上表现优于现有最优基线,有效提升模型泛化性与鲁棒性。

摘要:

尽管图神经网络(GNNs)已展现出通过各类消息传递机制从邻域节点收集图结构信息的强大能力,但含噪声、冗余的图数据会导致GNN泛化性差、鲁棒性脆弱,其性能因此受限。作为一类重要解决方案,图增强学习(Graph Augmentation Learning, GAL)近年来受到越来越多的关注。在已有的GAL方法中,训练阶段随机移除图中边的边丢弃方法是提升GNN鲁棒性的有效技术。然而,随机丢弃边往往会遗漏关键边,进而削弱消息传递的有效性。本文提出一种新型对抗性边丢弃方法ADEdgeDrop,该方法利用对抗性边预测器指导边的移除,可灵活集成到多种GNN骨干网络中。该方法采用对抗训练框架,边预测器利用由原始图转换得到的线图估计待丢弃的边,提升了边丢弃方法的可解释性。所提出的ADEdgeDrop通过随机梯度下降和投影梯度下降交替优化。在6个图基准数据集上的综合实验表明,所提ADEdgeDrop在各类GNN骨干网络上均优于现有最优基线,具备更优的泛化性与鲁棒性。

英文摘要:

Although Graph Neural Networks (GNNs) have exhibited the powerful ability to gather graph-structured information from neighborhood nodes via various message-passing mechanisms, the performance of GNNs is limited by poor generalization and fragile robustness caused by noisy and redundant graph data. As a prominent solution, Graph Augmentation Learning (GAL) has recently received increasing attention. Among prior GAL approaches, edge-dropping methods that randomly remove edges from a graph during training are effective techniques to improve the robustness of GNNs. However, randomly dropping edges often results in bypassing critical edges, consequently weakening the effectiveness of message passing. In this paper, we propose a novel adversarial edge-dropping method (ADEdgeDrop) that leverages an adversarial edge predictor guiding the removal of edges, which can be flexibly incorporated into diverse GNN backbones. Employing an adversarial training framework, the edge predictor utilizes the line graph transformed from the original graph to estimate the edges to be dropped, which improves the interpretability of the edge-dropping method. The proposed ADEdgeDrop is optimized alternately by stochastic gradient descent and projected gradient descent. Comprehensive experiments on six graph benchmark datasets demonstrate that the proposed ADEdgeDrop outperforms state-of-the-art baselines across various GNN backbones, demonstrating improved generalization and robustness.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑