Augmenting and Tuning Knowledge Graph Embeddings
arXiv:1907.01068
Abstract
Knowledge graph embeddings rank among the most successful methods for link prediction in knowledge graphs, i.e., the task of completing an incomplete collection of relational facts. A downside of these models is their strong sensitivity to model hyperparameters, in particular regularizers, which have to be extensively tuned to reach good performance [Kadlec et al., 2017]. We propose an efficient method for large scale hyperparameter tuning by interpreting these models in a probabilistic framework. After a model augmentation that introduces per-entity hyperparameters, we use a variational expectation-maximization approach to tune thousands of such hyperparameters with minimal additional cost. Our approach is agnostic to details of the model and results in a new state of the art in link prediction on standard benchmark data.
Published version, Conference on Uncertainty in Artificial Intelligence (UAI 2019)
References in corpus (8)
- Auto-Encoding Variational Bayes
- Practical Bayesian Optimization of Machine Learning Algorithms
- A Review of Relational Machine Learning for Knowledge Graphs
- ProjE: Embedding Projection for Knowledge Graph Completion
- SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions
- Bayesian Neural Word Embedding
- Bayesian Paragraph Vectors
- Improving Optimization for Models With Continuous Symmetry Breaking