DropEdge并非万无一失：面向符号图神经网络的有效增强方法
DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks
AI总结：
针对符号图稀疏与不平衡三角形导致SGNN链接符号预测受限的问题，提出SGA框架，通过候选边识别与有益候选选择进行结构增强，显著提升SGNN性能。
摘要：
本文讨论符号图，这类图使用标有正号或负号的边来建模友好或对立关系，重点关注链接符号预测任务。尽管符号图神经网络（SGNN）已经取得进展，但它们仍面临图稀疏性和不平衡三角形等挑战。作者提出使用数据增强（DA）技术来解决这些问题，不过由于缺乏辅助信息，许多现有方法并不适用于符号图。他们强调，随机DropEdge方法作为少数适用于符号图的DA方法，并不能提升链接符号预测性能。为此，他们提出了符号图增强（SGA）框架，该框架包含用于识别候选边的结构增强模块以及选择有益候选的策略，最终改进SGNN训练。实验结果表明，SGA显著提升了SGNN模型的性能，其中在Slashdot数据集上，SGCN的F1-micro显著提升了32.3%。
英文摘要：
The paper discusses signed graphs, which model friendly or antagonistic relationships using edges marked with positive or negative signs, focusing on the task of link sign prediction. While Signed Graph Neural Networks (SGNNs) have advanced, they face challenges like graph sparsity and unbalanced triangles. The authors propose using data augmentation (DA) techniques to address these issues, although many existing methods are not suitable for signed graphs due to a lack of side information. They highlight that the random DropEdge method, a rare DA approach applicable to signed graphs, does not enhance link sign prediction performance. In response, they introduce the Signed Graph Augmentation (SGA) framework, which includes a structure augmentation module to identify candidate edges and a strategy for selecting beneficial candidates, ultimately improving SGNN training. Experimental results show that SGA significantly boosts the performance of SGNN models, with a notable 32.3% improvement in F1-micro for SGCN on the Slashdot dataset.
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。
