TY - GEN
T1 - Rule-based Knowledge Graph Completion with Canonical Models
AU - Betz, Patrick
AU - Stepanova, Daria
AU - Gad-Elrab, Mohamed H.
AU - Meilicke, Christian
AU - Stuckenschmidt, Heiner
A2 - Ott, Simon
PY - 2023/10/21
Y1 - 2023/10/21
N2 - Rule-based approaches have proven to be an efficient and explainable method for knowledge base completion. Their predictive quality is on par with classic knowledge graph embedding models such as TransE or ComplEx, however, they cannot achieve the results of neural models proposed recently. The performance of a rule-based approach depends crucially on the solution of the rule aggregation problem, which is concerned with the computation of a score for a prediction that is generated by several rules. Within this paper, we propose a supervised approach to learn a reweighted confidence value for each rule to get an optimal explanation for the training set given a specific aggregation function. In particular, we apply our approach to two aggregation functions: We learn weights for a noisy-or multiplication and apply logistic regression, which computes the score of a prediction as a sum of these weights. Due to the simplicity of both models the final score is fully explainable. Our experimental results show that we can significantly improve the predictive quality of a rule-based approach. We compare our method with current state-of-the-art latent models that lack explainability, and achieve promising results.
AB - Rule-based approaches have proven to be an efficient and explainable method for knowledge base completion. Their predictive quality is on par with classic knowledge graph embedding models such as TransE or ComplEx, however, they cannot achieve the results of neural models proposed recently. The performance of a rule-based approach depends crucially on the solution of the rule aggregation problem, which is concerned with the computation of a score for a prediction that is generated by several rules. Within this paper, we propose a supervised approach to learn a reweighted confidence value for each rule to get an optimal explanation for the training set given a specific aggregation function. In particular, we apply our approach to two aggregation functions: We learn weights for a noisy-or multiplication and apply logistic regression, which computes the score of a prediction as a sum of these weights. Due to the simplicity of both models the final score is fully explainable. Our experimental results show that we can significantly improve the predictive quality of a rule-based approach. We compare our method with current state-of-the-art latent models that lack explainability, and achieve promising results.
U2 - 10.1145/3583780.3615042
DO - 10.1145/3583780.3615042
M3 - Conference Proceedings with Oral Presentation
SN - 979-8-4007-0124-5
T3 - 32nd ACM International Conference on Information and Knowledge Management
SP - 1971
EP - 1981
BT - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
T2 - CIKM '23: The 32nd ACM International Conference on Information and Knowledge Management
Y2 - 21 October 2023 through 25 October 2023
ER -