Interpretable Explanations for Probabilistic Inference in Markov Logic
Interpretable Explanations for Probabilistic Inference in Markov Logic
复制标题
DOI：
10.1109/bigdata52589.2021.9671572
复制
发表时间：
2021-12
期刊：
影响因子：
--
通讯作者：
Khan Mohammad Al Farabi;Somdeb Sarkhel;S. Dey;D. Venugopal
中科院分区：
文献类型：
--
作者：
Khan Mohammad Al Farabi;Somdeb Sarkhel;S. Dey;D. Venugopal
马尔可夫逻辑网络（mln）利用一阶逻辑和概率模型的结合来表示关系知识。在本文中，我们开发了一种解释mln中概率推理结果的方法。与解释黑盒分类器的LIME和SHAP等方法不同，解释M LN推理更难，因为数据是相互关联的。我们开发了一个解释框架，根据它们对边际似然的影响计算MLN公式的重要性权重。然而，事实证明，准确计算这些重要权重是一个难题，当MLN很大时，即使是近似抽样方法也不可靠，导致无法解释。因此，我们开发了一种方法，在这种方法中，我们将大型MLN减少为更简单的公式联盟，这些公式联盟近似地保留了关系依赖关系，并基于这些联盟生成解释。然后，我们权衡来自不同联盟的解释，并将它们合并为一个解释。我们的实验表明，与其他最先进的方法相比，我们的方法在几个文本处理问题中产生了更多可解释的解释。
Markov Logic Networks (MLNs) represent relational knowledge using a combination of first-order logic and probabilistic models. In this paper, we develop an approach to explain the results of probabilistic inference in MLNs. Unlike approaches such as LIME and SHAP that explain black-box classifiers, explaining M LN inference is harder since the data is interconnected. We develop an explanation framework that computes importance weights for MLN formulas based on their influence on the marginal likelihood. However, it turns out that computing these importance weights exactly is a hard problem and even approximate sampling methods are unreliable when the MLN is large resulting in non-interpretable explanations. Therefore, we develop an approach where we reduce the large MLN into simpler coalitions of formulas that approximately preserve relational dependencies and generate explanations based on these coalitions. We then weight explanations from different coalitions and combine them into a single explanation. Our experiments illustrate that our approach generates more interpretable explanations in several text processing problems as compared to other state-of-the-art methods.