用扩散模型生成图数据的反事实解释，让模型决策更透明。
Graph Diffusion Counterfactual Explanation
- 结合离散扩散模型与无分类器引导，生成结构变化最小的反事实图。
- 在离散分类和连续属性任务中均能生成分布合理、扰动小的反事实样本。
- 适合需要理解图模型决策过程的研究者或应用开发者。
基于图结构数据（如分子图或社交网络）的机器学习模型虽预测准确，却难以解释其决策原因。反事实解释通过寻找使模型预测改变的最近替代场景来解决此问题。尽管该方法在表格数据和计算机视觉中已广泛研究，但在图领域仍相对滞后。图数据的离散性与非欧几里得特性使得构造反事实解释极具挑战。本文提出图扩散反事实解释（Graph Diffusion Counterfactual Explanation），结合离散扩散模型与无分类器引导机制，实现对图数据的反事实生成。实验表明，该方法能可靠生成符合数据分布且结构扰动最小的反事实图，适用于离散分类目标与连续属性预测。
原文摘要 · Abstract (English)
Machine learning models that operate on graph-structured data, such as molecular graphs or social networks, often make accurate predictions but offer little insight into why certain predictions are made. Counterfactual explanations address this challenge by seeking the closest alternative scenario where the model's prediction would change. Although counterfactual explanations are extensively studied in tabular data and computer vision, the graph domain remains comparatively underexplored. Constructing graph counterfactuals is intrinsically difficult because graphs are discrete and non-euclidean objects. We introduce Graph Diffusion Counterfactual Explanation, a novel framework for generating counterfactual explanations on graph data, combining discrete diffusion models and classifier-free guidance. We empirically demonstrate that our method reliably generates in-distribution as well as minimally structurally different counterfactuals for both discrete classification targets and continuous properties.
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。