Probabilistic circuits (PCs) are models that allow exact and tractable probabilistic inference. In contrast to neural networks, they are often assumed to be well-calibrated and robust to out-of-distribution (OOD) data. In this paper, we show that PCs are in fact not robust to OOD data, i.e., they don't know what they don't know. We then show how this challenge can be overcome by model uncertainty quantification. To this end, we propose tractable dropout inference (TDI), an inference procedure to estimate uncertainty by deriving an analytical solution to Monte Carlo dropout (MCD) through variance propagation. Unlike MCD in neural networks, which comes at the cost of multiple network evaluations, TDI provides tractable sampling-free uncertainty estimates in a single forward pass. TDI improves the robustness of PCs to distribution shift and OOD data, demonstrated through a series of experiments evaluating the classification confidence and uncertainty estimates on real-world data.

翻译：概率电路（PCs）是一种支持精确且可处理的概率推理的模型。与神经网络不同，人们通常假设该类模型具有良好的校准性以及对分布外（OOD）数据的鲁棒性。本文研究表明，概率电路实际上对OOD数据不鲁棒，即它们无法感知自身未知性。随后，我们展示了如何通过模型不确定性量化来克服这一挑战。为此，提出了一种可处理的丢失推理（TDI）方法，通过方差传播推导蒙特卡洛丢失（MCD）的解析解来估计不确定性。与神经网络中需多次网络评估的MCD不同，TDI在单次前向传播中即可提供无需采样的可处理不确定性估计。通过在真实数据上评估分类置信度与不确定性的系列实验证明，TDI能提升概率电路对分布偏移和OOD数据的鲁棒性。