Exploring the Limits of Few-Shot Link Prediction in Knowledge Graphs

Dora Jambor, Komal Teru, Joelle Pineau, William L. Hamilton


Abstract
Real-world knowledge graphs are often characterized by low-frequency relations—a challenge that has prompted an increasing interest in few-shot link prediction methods. These methods perform link prediction for a set of new relations, unseen during training, given only a few example facts of each relation at test time. In this work, we perform a systematic study on a spectrum of models derived by generalizing the current state of the art for few-shot link prediction, with the goal of probing the limits of learning in this few-shot setting. We find that a simple, zero-shot baseline — which ignores any relation-specific information — achieves surprisingly strong performance. Moreover, experiments on carefully crafted synthetic datasets show that having only a few examples of a relation fundamentally limits models from using fine-grained structural information and only allows for exploiting the coarse-grained positional information of entities. Together, our findings challenge the implicit assumptions and inductive biases of prior work and highlight new directions for research in this area.
Anthology ID:
2021.eacl-main.245
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2816–2822
Language:
URL:
https://aclanthology.org/2021.eacl-main.245
DOI:
10.18653/v1/2021.eacl-main.245
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.245.pdf