发表机构
University of Southern California; Northeastern University（南加州大学; 东北大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出两阶段贪心框架G2I，将反事实解释转化为干预设计问题，在节点层面生成可操作反事实、网络层面解决预算约束下的DNF覆盖问题，实验显示其干预策略效率优于掩码方法。
AI 中文摘要
公共卫生与社会科学领域的现实决策可从预测模型中极大获益，但将预测结果转化为有效干预措施需解释模型行为。图神经网络（GNN）适用于建模关系数据，然而现有解释方法大多在节点层面操作，无法支持可操作的网络层面干预设计。现有反事实GNN解释器如CF-GNNExplainer和CF²依赖对特征与边的连续掩码优化，隐含假设边操作可行，可能将精力分配至不可变或不可操作属性，且计算开销大；此外，非AI领域专家的领域专家难以理解这类解释方法本身。简单方法能否生成优质解释？为探究此问题，本文将反事实解释重新表述为干预设计问题：在局部层面，通过贪心搜索生成反事实，直接识别节点特征与邻居层面条件的最小、可操作变化；本文推导了贪心搜索提供保证的条件，经实证验证这些条件近似满足，这些反事实被转化为适用于现实干预的可解释规则。在网络层面，本文将干预选择表述为预算约束下的析取范式（DNF）覆盖问题，该问题非递减且近似子模，可实现带理论保证的贪心算法。在合成图与真实自杀风险网络上的实验表明，本文方法可生成可扩展、高性价比的干预策略，与基于掩码的反事实方法相比效率显著提升。
英文摘要
Real-world decision-making in public health and social science can greatly benefit from predictive models, yet translating predictions into effective interventions requires explaining the model behavior. While Graph Neural Networks (GNNs) are well-suited for modeling relational data, existing explanation methods largely operate at the node level and fall short of supporting actionable, network-level intervention design. Existing counterfactual GNN explainers, such as CF-GNNExplainer and CF$^2$, rely on continuous mask optimization over features and edges, which implicitly assume feasible edge manipulation, may allocate effort to immutable or non-actionable attributes, and incur substantial computational overhead. Further, the method of arriving at the explanation itself is difficult to explain to a domain specialist who is not an AI expert. Can simple methods generate good explanations? To explore this, we reframe counterfactual explanation as an intervention design problem. At the local level, we generate counterfactuals via a greedy search that directly identifies minimal, actionable changes to node features and neighbor-level conditions. We derive conditions under which the greedy search provides guarantees, and empirically show that these conditions are approximately met. These counterfactuals are converted into interpretable rules suitable for real-world intervention. At the network level, we formulate intervention selection as a Disjunctive Normal Form (DNF) coverage problem under a budget constraint, which is nondecreasing and approximately submodular, enabling a greedy algorithm with theoretical guarantees. Experiments on synthetic graphs and real-world suicide risk networks demonstrate that our approach produces scalable, cost-effective intervention strategies with significantly improved efficiency over mask-based counterfactual methods.
Comments11 pages, 3 figures. Accepted at the 35th ACM International Conference on Information and Knowledge Management (CIKM 2026)
