Cycle Representation Learning for Inductive Relation Prediction
Authors:
- Zuoyu YanZYZuoyu Yan
- Tengfei MaTMTengfei Ma
- Liangcai GaoLGLiangcai Gao
- Zhi TangZTZhi Tang
- Chao ChenCCChao Chen
Preprint
Abstract
In recent years, algebraic topology and its modern development, the theory of persistent homology, has shown great potential in graph representation learning. In this paper, based on the mathematics of algebraic topology, we propose a novel solution for inductive relation prediction, an important learning task for knowledge graph completion. To predict the relation between two entities, one can use the existence of rules, namely a sequence of relations. Previous works view rules as paths and primarily focus on the searching of paths between entities. The space of rules is huge, and one has to sacrifice either efficiency or accuracy. In this paper, we consider rules as cycles and show that the space of cycles has a unique structure based on the mathematics 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.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Line Graph Neural Networks for Link PredictionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Knowledge Graph Completion: A ReviewIEEE Access, 2020
- A Topological Representation of Branching Neuronal MorphologiesNeuroinformatics, 2017
- Single-cell topological RNA-seq analysis reveals insights into cellular differentiation and developmentNature Biotechnology, 2017
- Clique topology reveals intrinsic geometric structure in neural correlationsProceedings of the National Academy of Sciences, 2015
- Homological scaffolds of brain functional networksJournal of The Royal Society Interface, 2014
- Topology of viral evolutionProceedings of the National Academy of Sciences, 2013
- Hardness Results for Homology LocalizationDiscrete & Computational Geometry, 2011
- Optimal Homologous Cycles, Total Unimodularity, and Linear ProgrammingSIAM Journal on Computing, 2011
- Measuring and computing natural generators for homology groupsComputational Geometry, 2010