InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions

11/01/2019
by   Shikhar Vashishth, et al.
30

Most existing knowledge graphs suffer from incompleteness, which can be alleviated by inferring missing links based on known facts. One popular way to accomplish this is to generate low-dimensional embeddings of entities and relations, and use these to make inferences. ConvE, a recently proposed approach, applies convolutional filters on 2D reshapings of entity and relation embeddings in order to capture rich interactions between their components. However, the number of interactions that ConvE can capture is limited. In this paper, we analyze how increasing the number of these interactions affects link prediction performance, and utilize our observations to propose InteractE. InteractE is based on three key ideas – feature permutation, a novel feature reshaping, and circular convolution. Through extensive experiments, we find that InteractE outperforms state-of-the-art convolutional link prediction baselines on FB15k-237. Further, InteractE achieves an MRR score that is 9 7.5 respectively. The results validate our central hypothesis – that increasing feature interaction is beneficial to link prediction performance. We make the source code of InteractE available to encourage reproducible research.

READ FULL TEXT

page 2

page 6

research
08/21/2018

Hypernetwork Knowledge Graph Embeddings

Knowledge graphs are large graph-structured databases of facts, which ty...
research
06/27/2021

KGRefiner: Knowledge Graph Refinement for Improving Accuracy of Translational Link Prediction Methods

Link prediction is the task of predicting missing relations between enti...
research
09/03/2022

Disconnected Emerging Knowledge Graph Oriented Inductive Link Prediction

Inductive link prediction (ILP) is to predict links for unseen entities ...
research
01/04/2022

CHERRY: a Computational metHod for accuratE pRediction of virus-pRokarYotic interactions using a graph encoder-decoder model

Prokaryotic viruses, which infect bacteria and archaea, are key players ...
research
12/20/2021

Self-attention Presents Low-dimensional Knowledge Graph Embeddings for Link Prediction

Recently, link prediction problem, also known as knowledge graph complet...
research
06/29/2021

Convolutional Hypercomplex Embeddings for Link Prediction

Knowledge graph embedding research has mainly focused on the two smalles...
research
05/02/2019

Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications

Representing entities and relations in an embedding space is a well-stud...

Please sign up or login with your details

Forgot password? Click here to reset