Rajarshi Das, Ameya Godbole, Shehzaad Dhuliawala, Manzil Zaheer, Andrew McCallum.

doi:10.24432/C52S3K

TL;DR

We present a surprisingly simple yet accurate approach to reasoning in knowledge graphs (KGs) that requires \emph{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 approach finds multiple \textit{graph path patterns} that connect similar source entities through the given relation, and looks for pattern matches starting from the query source. 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.

Citation

@inproceedings{
das2020nonparametric,
title={Non-Parametric Reasoning in Knowledge Bases},
author={Rajarshi Das and Ameya Godbole and Shehzaad Dhuliawala and Manzil Zaheer and Andrew McCallum},
booktitle={Automated Knowledge Base Construction},
year={2020},
url={https://openreview.net/forum?id=AEY9tRqlU7},
doi={10.24432/C52S3K}
}