Paper Info
Title
Simple and Effective Relation-based Embedding Propagation for Knowledge Representation Learning.
Abstract
Relational graph neural networks have garnered particular attention to encode graph context in knowledge graphs (KGs). Although they achieved competitive performance on small KGs, how to efficiently and effectively utilize graph context for large KGs remains an open problem. To this end, we propose the Relation-based Embedding Propagation (REP) method. It is a post-processing technique to adapt pre-trained KG embeddings with graph context. As relations in KGs are directional, we model the incoming head context and the outgoing tail context separately. Accordingly, we design relational context functions with no external parameters. Besides, we use averaging to aggregate context information, making REP more computation-efficient. We theoretically prove that such designs can avoid information distortion during propagation. Extensive experiments also demonstrate that REP has significant scalability while improving or maintaining prediction quality. Notably, it averagely brings about 10% relative improvement to triplet-based embedding methods on OGBL-WikiKG2 and takes 5%-83% time to achieve comparable results as the state-of-the-art GC-OTE.
Year
DOI
Venue
2022
10.24963/ijcai.2022/382
European Conference on Artificial Intelligence
Keywords
DocType
Citations 
Knowledge Representation and Reasoning: Applications,Knowledge Representation and Reasoning: Learning and reasoning,Knowledge Representation and Reasoning: Other,Knowledge Representation and Reasoning: Semantic Web,Machine Learning: Representation learning
Conference
0
PageRank 
References 
Authors
0.34
0
10
Name
Order
Citations
PageRank
Huijuan Wang100.34
Siming Dai200.68
Weiyue Su301.69
Hui Zhong400.34
Zeyang Fang500.68
Zhengjie Huang623.75
Shikun Feng753.78
Zeyu Chen800.34
Yu Sun900.34
Dianhai Yu1001.01