arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.16375cs.LG
收藏

DyExplainer:可解释的动态图神经网络

DyExplainer: Explainable Dynamic Graph Neural Networks

Pennsylvania State University(宾夕法尼亚州立大学);Florida International University(佛罗里达国际大学);NEC Labs America(NEC美国实验室)

Tianchun Wang, Dongsheng Luo, Wei Cheng, Haifeng Chen, Xiang Zhang

AI总结:

提出DyExplainer方法,通过稀疏注意力和对比学习实时解释动态图神经网络,在保持解释属性的同时提升链路预测精度。

摘要:

图神经网络(GNNs)因其从图结构数据中捕获表示的出色能力而再次成为热门研究课题。然而,GNNs的黑盒特性在理解和信任这些模型方面带来了重大挑战,从而限制了它们在关键任务场景中的实际应用。尽管近年来在解释GNNs领域取得了实质性进展,但这些研究大多集中在静态图上,对动态GNNs的解释在很大程度上尚未被探索。动态GNNs具有不断演化的图结构,构成了独特的挑战,需要额外的努力来有效捕获时间依赖性和结构关系。为了应对这一挑战,我们提出了DyExplainer,一种实时解释动态GNNs的新方法。DyExplainer训练一个动态GNN主干网络以在每个快照处提取图的表示,同时通过稀疏注意力技术探索结构关系和时间依赖性。为了保持解释的期望属性,如结构一致性和时间连续性,我们通过对比学习技术增强了我们的方法,以提供先验引导的正则化。为了建模更长期的时间依赖性,我们开发了一种基于缓冲区的实时更新方案进行训练。我们在各种数据集上的大量实验结果表明了DyExplainer的优越性,它不仅提供了对模型预测的忠实可解释性,还显著提高了模型预测精度,这在链路预测任务中得到了证明。

英文摘要:

Graph Neural Networks (GNNs) resurge as a trending research subject owing to their impressive ability to capture representations from graph-structured data. However, the black-box nature of GNNs presents a significant challenge in terms of comprehending and trusting these models, thereby limiting their practical applications in mission-critical scenarios. Although there has been substantial progress in the field of explaining GNNs in recent years, the majority of these studies are centered on static graphs, leaving the explanation of dynamic GNNs largely unexplored. Dynamic GNNs, with their ever-evolving graph structures, pose a unique challenge and require additional efforts to effectively capture temporal dependencies and structural relationships. To address this challenge, we present DyExplainer, a novel approach to explaining dynamic GNNs on the fly. DyExplainer trains a dynamic GNN backbone to extract representations of the graph at each snapshot, while simultaneously exploring structural relationships and temporal dependencies through a sparse attention technique. To preserve the desired properties of the explanation, such as structural consistency and temporal continuity, we augment our approach with contrastive learning techniques to provide priori-guided regularization. To model longer-term temporal dependencies, we develop a buffer-based live-updating scheme for training. The results of our extensive experiments on various datasets demonstrate the superiority of DyExplainer, not only providing faithful explainability of the model predictions but also significantly improving the model prediction accuracy, as evidenced in the link prediction task.

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。

↑