AINeutralarXiv – CS AI · 6h ago6/10
🧠
DeepSWIP: Quotient-WMC Counterfactuals for Neural Probabilistic Logic Programs
DeepSWIP introduces a novel counterfactual reasoning framework for DeepProbLog programs by combining neural perception with probabilistic logic through weighted model counting. The approach achieves 2.14× inference speedup while enabling causal intervention analysis, demonstrated through experiments on visual reasoning and fairness estimation tasks.