A Simple Approach to Case-Based Reasoning in Knowledge Bases

by   Rajarshi Das, et al.

We present a surprisingly simple yet accurate approach to reasoning in knowledge graphs (KGs) that requires no training, and is reminiscent of case-based reasoning in classical artificial intelligence (AI). Consider the task of finding a target entity given a source entity and a binary relation. Our non-parametric approach derives crisp logical rules for each query by finding multiple graph path patterns that connect similar source entities through the given relation. Using our method, we obtain new state-of-the-art accuracy, outperforming all previous models, on NELL-995 and FB-122. We also demonstrate that our model is robust in low data settings, outperforming recently proposed meta-learning approaches


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

A case-based reasoning (CBR) system solves a new problem by retrieving `...

Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning

Knowledge bases (KB), both automatically and manually constructed, are o...

Standing on the Shoulders of Predecessors: Meta-Knowledge Transfer for Knowledge Graphs

Knowledge graphs (KGs) have become widespread, and various knowledge gra...

Bootleg: Chasing the Tail with Self-Supervised Named Entity Disambiguation

A challenge for named entity disambiguation (NED), the task of mapping t...

Entity Alignment with Reliable Path Reasoning and Relation-Aware Heterogeneous Graph Transformer

Entity Alignment (EA) has attracted widespread attention in both academi...

Towards Robust Reasoning over Knowledge Graphs

Answering complex logical queries over large-scale knowledge graphs (KGs...

Variational Knowledge Graph Reasoning

Inferring missing links in knowledge graphs (KG) has attracted a lot of ...

Please sign up or login with your details

Forgot password? Click here to reset