基于因果模型精准解释神经网络预测，避免依赖关系导致的误导
Computing Actual Causes for Neural Network Predictions under Structured Causal Inputs
- 用布尔结构因果模型建模输入依赖，定义实际原因
- 在2.3×10¹³个候选对上高效计算最小实际原因，180秒内完成
- 适合需要可信解释的高风险领域，如医疗或金融决策
解释神经网络预测是可信AI的核心挑战。现有方法如特征归因或最小充分集通常将输入特征视为独立，当输入存在结构化依赖时可能产生误导性解释。本文通过形式化为Halpern-Pearl（HP）实际原因，并利用布尔结构因果模型（SCM）建模输入依赖，采用边界传播与分支定界技术计算HP原因，提供完备性与最小性形式保证。实验表明，在规模高达28节点的SCM上，我们能在180秒内处理最多2.3×10¹³个（原因，背景）候选对，显著优于暴力搜索和整数线性规划基线，且随图规模增长超越启发式搜索。案例研究显示，忽略输入依赖会夸大原因数量，其中14.9%为虚假原因。
原文摘要 · Abstract (English)
Explaining the predictions of neural networks is a central challenge in trustworthy AI. Existing explanation methods, such as those based on feature attribution or minimal sufficient sets, typically treat input features as independent, which can yield misleading explanations when inputs exhibit structured dependencies. We address this by formalizing explanations as Halpern-Pearl (HP) actual causes, modeling input dependencies using Boolean Structural Causal Models (SCMs). We compute HP causes by applying bound propagation and branch-and-bound techniques, while providing formal guarantees of completeness and minimality. Our experiments show that we substantially outperform brute-force and ILP baselines in scalability, and outperform heuristic search as graph size grows, computing all minimal actual causes on instances with search spaces of up to $2.3\times10^{13}$ candidate (cause, contingency) pairs, on SCMs with up to 28 nodes, within a 180s per-instance budget. In a case study, we further show that ignoring input dependencies inflates the number of reported causes, 14.9% of which are spurious under our SCM.
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。