DeepProbLog 等神经符号系统将神经感知与概率逻辑相结合,，但标准推理是关联的。反事实推理还需要干预和证据的因果语义。我们为 DeepProbLog 程序引入了 DeepSWIP, 单一世界反事实语义。使用神经物化,，我们将固定上下文神经谓词减少为普通的ProbLog选择,，应用单一世界干预程序(SWIPs),，并通过单个转换程序上的加权模型计数(WMC)来计算反事实。在有限基础和唯一支持模型假设下，, DeepSWIP 相对于学习到的物化 FCM 是准确的。 ProbLog 条件的标准商-WMC 形式可识别主动神经概率，并解释干预清洁, 校准灵敏度, 和罕见证据的不稳定性。 MPI3D 上的实验证实了针对 DeepTwin 结构的转换，如预测的那样，查询次数为 12,000,，并且由于避免了 Twin的 内源重复，推理速度提高了 2.14$\times$。 SUMO HOV 实验表明，神经校准退化使插件估计存在偏差,，而正确范围的随机策略 AIPW 估计器消除了总体平均值和 ATE 估计值的大部分一阶偏差。代码位于此 https URL。
Neurosymbolic systems such as DeepProbLog combine neural perception with probabilistic logic, but standard inference is associational. Counterfactual reasoning additionally requires a causal semantics for interventions and evidence. We introduce DeepSWIP, a single-world counterfactual semantics for DeepProbLog programs. Using neural materialization, we reduce fixed-context neural predicates to ordinary ProbLog choices, apply Single World Intervention Programs (SWIPs), and compute counterfactuals by weighted model counting (WMC) over a single transformed program. Under finite grounding and unique-supported-model assumptions, DeepSWIP is exact relative to the learned materialized FCM. The standard quotient-WMC form of ProbLog conditionals identifies active neural probabilities and explains intervention cleaning, calibration sensitivity, and rare-evidence instability. Experiments on MPI3D confirm the transformation against a DeepTwin construction against 12,000 queries, as predicted and a 2.14$\times$ inference speedup from avoiding the Twin的 endogenous duplication. A SUMO HOV experiment shows that neural calibration degradation biases plug-in estimates, while a correctly scoped randomized-policy AIPW estimator removes most first-order bias for population mean and ATE estimands. Code is at this https URL.
科目:人工智能(cs.AI)
Subjects: Artificial Intelligence (cs.AI)