对比6种图神经网络反事实解释方法，找出各自优劣。
A Comparative Study of Counterfactual Explainers for Graph Neural Networks Enabling Multiple Types of Graph Edit
- 系统比较6种可增删边的图解释方法
- 在真实与合成数据上验证解释质量差异
- 为后续研究提供方法选择依据
图结构数据的反事实解释旨在确定最小且合理的图修改，以改变模型预测结果。尽管已有支持增删边的反事实解释方法，但仍缺乏通用高效的解决方案，尤其在解释质量方面。现有方法在解释规模、覆盖范围和质量之间存在权衡，表现各异。为此，本文在涵盖二分类与多分类任务的多种真实与合成数据集上，系统比较了六种前沿模型，并采用多样化的定量与定性指标评估其性能，旨在明确各方法的优势与局限，为未来研究提供指导。
原文摘要 · Abstract (English)
Counterfactual explanations for graph-structured data seek to determine minimal and realistic modifications required in an input graph to alter a model's prediction to a predefined output. Although counterfactual explainers that support modifying the graph by both adding and removing edges have recently emerged, there is still a lack of general and efficient methods, especially when considering the quality of the generated explanations. Moreover, the problem remains far from solved, as existing methods exhibit different strengths and weaknesses, often trading off between explanation size, coverage and quality. For this reason, it is important to identify where each method performs well and where it falls short, so as to guide future research in the field. Thus, our study compares six state-of-the-art (SOTA) models on a diverse set of real-world and synthetic datasets, covering both binary and multi-class graph and node classification tasks, and evaluates their performance using diverse quantitative and qualitative 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。