Paper Info
Title
Analysis of the Impact of Negative Sampling on Link Prediction in Knowledge Graphs.
Abstract
Knowledge graphs are large, useful, but incomplete knowledge repositories. They encode knowledge through entities and relations which define each other through the connective structure of the graph. This has inspired methods for the joint embedding of entities and relations in continuous low-dimensional vector spaces, that can be used to induce new edges in the graph, i.e., link prediction in knowledge graphs. Learning these representations relies on contrasting positive instances with negative ones. Knowledge graphs include only positive relation instances, leaving the door open for a variety of methods for selecting negative examples. In this paper we present an empirical study on the impact of negative sampling on the learned embeddings, assessed through the task of link prediction. We use state-of-the-art knowledge graph embeddings -- rescal , TransE, DistMult and ComplEX -- and evaluate on benchmark datasets -- FB15k and WN18. We compare well known methods for negative sampling and additionally propose embedding based sampling methods. We note a marked difference in the impact of these sampling methods on the two datasets, with the traditional corrupting positives method leading to best results on WN18, while embedding based methods benefiting the task on FB15k.
Year
Venue
Field
2017
arXiv: Artificial Intelligence
ENCODE,Data mining,Graph,Incomplete knowledge,Vector space,Knowledge graph,Embedding,Computer science,Sampling (statistics),Artificial intelligence,Empirical research,Machine learning
DocType
Volume
Citations 
Journal
abs/1708.06816
2
PageRank 
References 
Authors
0.36
23
2
Name
Order
Citations
PageRank
Bhushan Kotnis144.12
Vivi Nastase252341.30