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.

14 pages

References in corpus (2)

• Compositional Vector Space Models for Knowledge Base Completion
• Knowledge Graph Completion via Complex Tensor Factorization

Cited by in corpus (11)

• Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
• Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework
• DGL-KE: Training Knowledge Graph Embeddings at Scale
• Benchmarking Network Embedding Models for Link Prediction: Are We Making Progress?
• Probability Calibration for Knowledge Graph Embedding Models
• Neighborhood Matching Network for Entity Alignment
• EvalNE: A Framework for Evaluating Network Embeddings on Link Prediction
• Distributional Negative Sampling for Knowledge Base Completion
• Improving Skip-Gram based Graph Embeddings via Centrality-Weighted Sampling
• Are Missing Links Predictable? An Inferential Benchmark for Knowledge Graph Completion
• Statistical Analysis of Multi-Relational Network Recovery