Neighborhood Intervention Consistency: Measuring Confidence for Knowledge Graph Link Prediction
Neighborhood Intervention Consistency: Measuring Confidence for Knowledge Graph Link Prediction
Kai Wang, Yu Liu, Quan Z. Sheng
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Main Track. Pages 2090-2096.
https://doi.org/10.24963/ijcai.2021/288
Link prediction based on knowledge graph embeddings (KGE) has recently drawn a considerable momentum. However, existing KGE models suffer from insufficient accuracy and hardly evaluate the confidence probability of each predicted triple. To fill this critical gap, we propose a novel confidence measurement method based on causal intervention, called Neighborhood Intervention Consistency (NIC). Unlike previous confidence measurement methods that focus on the optimal score in a prediction, NIC actively intervenes in the input entity vector to measure the robustness of the prediction result. The experimental results on ten popular KGE models show that our NIC method can effectively estimate the confidence score of each predicted triple. The top 10% triples with high NIC confidence can achieve 30% higher accuracy in the state-of-the-art KGE models.
Keywords:
Knowledge Representation and Reasoning: Action, Change and Causality
Knowledge Representation and Reasoning: Reasoning about Knowledge and Belief
Knowledge Representation and Reasoning: Semantic Web