A Topological View of Rule Learning in Knowledge Graphs

10/06/2021
by   Zuoyu Yan, et al.
3

Inductive relation prediction is an important learning task for knowledge graph completion. One can use the existence of rules, namely a sequence of relations, to predict the relation between two entities. Previous works view rules as paths and primarily focus on the searching of paths between entities. The space of paths is huge, and one has to sacrifice either efficiency or accuracy. In this paper, we consider rules in knowledge graphs as cycles and show that the space of cycles has a unique structure based on the theory of algebraic topology. By exploring the linear structure of the cycle space, we can improve the searching efficiency of rules. We propose to collect cycle bases that span the space of cycles. We build a novel GNN framework on the collected cycles to learn the representations of cycles, and to predict the existence/non-existence of a relation. Our method achieves state-of-the-art performance on benchmarks.

READ FULL TEXT
research
02/24/2017

Embedding Knowledge Graphs Based on Transitivity and Antisymmetry of Rules

Representation learning of knowledge graphs encodes entities and relatio...
research
06/07/2022

Learning Attention-based Representations from Multiple Patterns for Relation Prediction in Knowledge Graphs

Knowledge bases, and their representations in the form of knowledge grap...
research
11/16/2019

Inductive Relation Prediction on Knowledge Graphs

Inferring missing edges in multi-relational knowledge graphs is a fundam...
research
11/20/2019

Rule-Guided Compositional Representation Learning on Knowledge Graphs

Representation learning on a knowledge graph (KG) is to embed entities a...
research
09/16/2020

Type-augmented Relation Prediction in Knowledge Graphs

Knowledge graphs (KGs) are of great importance to many real world applic...
research
02/24/2018

Improving Recall of In Situ Sequencing by Self-Learned Features and a Graphical Model

Image-based sequencing of mRNA makes it possible to see where in a tissu...
research
04/10/2023

Incorporating Structured Sentences with Time-enhanced BERT for Fully-inductive Temporal Relation Prediction

Temporal relation prediction in incomplete temporal knowledge graphs (TK...

Please sign up or login with your details

Forgot password? Click here to reset