Probabilistic Case-based Reasoning for Open-World Knowledge Graph Completion

A case-based reasoning (CBR) system solves a new problem by retrieving `cases' that are similar to the given problem. If such a system can achieve high accuracy, it is appealing owing to its simplicity, interpretability, and scalability. In this paper, we demonstrate that such a system is achievable for reasoning in knowledge-bases (KBs). Our approach predicts attributes for an entity by gathering reasoning paths from similar entities in the KB. Our probabilistic model estimates the likelihood that a path is effective at answering a query about the given entity. The parameters of our model can be efficiently computed using simple path statistics and require no iterative optimization. Our model is non-parametric, growing dynamically as new entities and relations are added to the KB. On several benchmark datasets our approach significantly outperforms other rule learning approaches and performs comparably to state-of-the-art embedding-based approaches. Furthermore, we demonstrate the effectiveness of our model in an "open-world" setting where new entities arrive in an online fashion, significantly outperforming state-of-the-art approaches and nearly matching the best offline method. Code available at https://github.com/ameyagodbole/Prob-CBR

PDF Abstract Findings of 2020 PDF Findings of 2020 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Link Prediction FB122 Prob-CBR HITS@3 74.2 # 1
Hits@5 76.0 # 1
Hits@10 78.2 # 1
MRR 72.7 # 1
Link Prediction NELL-995 Prob-CBR MRR 0.81 # 1
Hits@1 0.77 # 1
Hits@10 0.89 # 1
HITS@3 0.85 # 1
Link Prediction WN18RR ProbCBR MRR 0.48 # 27
Hits@10 0.55 # 39
Hits@3 0.49 # 26
Hits@1 0.43 # 30

Methods


No methods listed for this paper. Add relevant methods here