提出新框架，让图神经网络解释更直观可靠。
A Completion-Aware Framework for Impactful Counterfactual Explainability in Graph Neural Networks
- 结合真实解释与缺边预测提升解释质量
- 在多个数据集上优于现有方法，效果稳定
- 适合需要可信解释的图模型应用者
本文提出一种通用、模型无关、局部级别的图神经网络反事实可解释性新框架。尽管近年已有支持增删边的反事实解释器，但高效且高质量的通用解决方案仍不足，尤其在解释生成质量方面。本方法融合事实解释进展与基于链接预测研究的缺边预测模型，以提升解释的质量、鲁棒性和直观性。在真实世界与合成图分类基准（包括二分类和多标签）上的多维度实验表明，该方法在多种指标上均显著优于当前最优基线。
原文摘要 · Abstract (English)
In this study, we propose a novel pipeline for generic, model-agnostic, local-level counterfactual explainability in graph neural networks (GNNs). Although counterfactual explainers capable of both adding and removing edges have emerged in recent years, the need for generic and efficient solutions remains unmet, particularly concerning qualitative explanation generation. Our approach couples progress in factual explainability with missing edge prediction models rooted in link prediction research, in order to enhance the quality, robustness and intuitiveness of explanations. A multi-faceted experimental analysis conducted on real-world and synthetic graph classification benchmarks, both binary and multi-label, demonstrates the advancements in comparison to state-of-the-art baselines across diverse metrics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。