CQD-SHAP: Explainable Complex Query Answering via Shapley Values
This addresses the need for interpretability in complex query answering systems, which are often black-box, by providing explanations for users, though it is incremental as it builds on existing neurosymbolic methods.
The paper tackles the problem of explaining complex query answering over incomplete knowledge graphs by proposing CQD-SHAP, a framework that uses Shapley values to compute the contribution of each query part to answer rankings, showing effectiveness for most query types in automated evaluations.
Complex query answering (CQA) goes beyond the well-studied link prediction task by addressing more sophisticated queries that require multi-hop reasoning over incomplete knowledge graphs (KGs). Research on neural and neurosymbolic CQA methods is still an emerging field. Almost all of these methods can be regarded as black-box models, which may raise concerns about user trust. Although neurosymbolic approaches like CQD are slightly more interpretable, allowing intermediate results to be tracked, the importance of different parts of the query remains unexplained. In this paper, we propose CQD-SHAP, a novel framework that computes the contribution of each query part to the ranking of a specific answer. This contribution explains the value of leveraging a neural predictor that can infer new knowledge from an incomplete KG, rather than a symbolic approach relying solely on existing facts in the KG. CQD-SHAP is formulated based on Shapley values from cooperative game theory and satisfies all the fundamental Shapley axioms. Automated evaluation of these explanations in terms of necessary and sufficient explanations, and comparisons with various baselines, shows the effectiveness of this approach for most query types.