SnapE -- Training Snapshot Ensembles of Link Prediction Models
This work addresses the need for more robust and efficient link prediction models in knowledge graphs, though it is incremental as it adapts an existing ensemble technique to a specific domain.
The paper tackles the problem of link prediction in knowledge graphs by introducing a snapshot ensemble approach, which constantly outperforms single models across four datasets while maintaining the same training time.
Snapshot ensembles have been widely used in various fields of prediction. They allow for training an ensemble of prediction models at the cost of training a single one. They are known to yield more robust predictions by creating a set of diverse base models. In this paper, we introduce an approach to transfer the idea of snapshot ensembles to link prediction models in knowledge graphs. Moreover, since link prediction in knowledge graphs is a setup without explicit negative examples, we propose a novel training loop that iteratively creates negative examples using previous snapshot models. An evaluation with four base models across four datasets shows that this approach constantly outperforms the single model approach, while keeping the training time constant.