Probabilistic inferences distill knowledge from graphs to aid human make important decisions. Due to the inherent uncertainty in the model and the complexity of the knowledge, it is desirable to help the end-users understand the inference outcomes. Different from deep or high-dimensional parametric models, the lack of interpretability in graphical models is due to the cyclic and long-range dependencies and the byzantine inference procedures. Prior works did not tackle cycles and make textit{the} inferences interpretable. To close the gap, we formulate the problem of explaining probabilistic inferences as a constrained cross-entropy minimization problem to find simple subgraphs that faithfully approximate the inferences to be explained. We prove that the optimization is NP-hard, while the objective is not monotonic and submodular to guarantee efficient greedy approximation. We propose a general beam search algorithm to find simple trees to enhance the interpretability and diversity in the explanations, with parallelization and a pruning strategy to allow efficient search on large and dense graphs without hurting faithfulness. We demonstrate superior performance on 10 networks from 4 distinct applications, comparing favorably to other explanation methods. Regarding the usability of the explanation, we visualize the explanation in an interface that allows the end-users to explore the diverse search results and find more personalized and sensible explanations.
تحميل البحث