CauseKG: A Framework Enhancing Causal Inference with Implicit Knowledge Deduced from Knowledge Graphs

Causal inference is a crucial technique for deriving causal relationships from data and distinguishing causation from correlations. Causal inference frameworks rely on structured data, usually represented in flat tables or relational models. These frameworks estimate causal effects solely based on explicit facts, overlooking implicit information in the data, which can result in inaccurate causal estimations. Knowledge graphs (KGs) inherently capture implicit information through entailment regimes applied to explicit facts, providing a unique opportunity to leverage implicit knowledge. However, existing frameworks are inapplicable to KGs due to their semi-structured nature. CauseKG is a causal inference framework designed to address the intricacies of KGs and seamlessly integrate implicit information using entailment techniques specific to KGs, providing a more accurate causal inference process.We empirically evaluate the efficacy of CauseKG over benchmarks created from synthetic and real-world datasets. The results suggest that CauseKG can yield lower Mean Absolute Error in estimating causal effects compared to state-of-the-art methods. The empirical results indicate CauseKG's ability to address causal questions in different domains. This research underscores the importance of extending causal inference techniques to KGs, emphasizing the enhanced accuracy achievable through the integration of implicit and explicit information.