将对抗攻击思路融入图神经网络解释，生成更真实可信的反事实解释。
ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural Networks
- 融合对抗攻击的边添加与解释的边删除，统一生成策略。
- 在有限扰动下同时优化准确度、稀疏性和合理性，解释更可信。
- 适合需要可解释性的图模型应用，如金融风控、医疗诊断。
反事实解释通过识别能改变模型预测的最小修改，直观地解释图神经网络（GNN）的决策，回答“什么必须不同才能得到不同结果？”的问题。本文提出一种新框架 ATEX-CF，将对抗攻击技术与反事实解释生成相统一——二者目标均为翻转节点预测，但扰动策略不同：对抗攻击常使用边添加，而传统反事实方法多采用边删除。不同于将解释与攻击分离的传统方法，本方法理论驱动地高效结合边添加与删除，在有限扰动预算下联合优化忠实性、稀疏性和合理性，生成实例级且具信息量的解释。在合成与真实世界节点分类基准上的实验表明，ATEX-CF 能生成忠实、简洁且合理的解释，验证了将对抗洞察融入反事实推理对 GNN 解释的有效性。
原文摘要 · Abstract (English)
Counterfactual explanations offer an intuitive way to interpret graph neural networks (GNNs) by identifying minimal changes that alter a model's prediction, thereby answering "what must differ for a different outcome?". In this work, we propose a novel framework, ATEX-CF that unifies adversarial attack techniques with counterfactual explanation generation-a connection made feasible by their shared goal of flipping a node's prediction, yet differing in perturbation strategy: adversarial attacks often rely on edge additions, while counterfactual methods typically use deletions. Unlike traditional approaches that treat explanation and attack separately, our method efficiently integrates both edge additions and deletions, grounded in theory, leveraging adversarial insights to explore impactful counterfactuals. In addition, by jointly optimizing fidelity, sparsity, and plausibility under a constrained perturbation budget, our method produces instance-level explanations that are both informative and realistic. Experiments on synthetic and real-world node classification benchmarks demonstrate that ATEX-CF generates faithful, concise, and plausible explanations, highlighting the effectiveness of integrating adversarial insights into counterfactual reasoning for GNNs.
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。