Learning Knowledge Graph Embeddings with Type Regularizer
This work addresses the challenge of improving relation learning in knowledge bases for AI applications, but it is incremental as it builds on an existing model with a new regularization technique.
The paper tackled the problem of learning knowledge graph embeddings by incorporating entity type information as a regularization factor into the RESCAL model, resulting in increased performance measured by mean reciprocal rank and hits@N metrics.
Learning relations based on evidence from knowledge bases relies on processing the available relation instances. Many relations, however, have clear domain and range, which we hypothesize could help learn a better, more generalizing, model. We include such information in the RESCAL model in the form of a regularization factor added to the loss function that takes into account the types (categories) of the entities that appear as arguments to relations in the knowledge base. We note increased performance compared to the baseline model in terms of mean reciprocal rank and hits@N, N = 1, 3, 10. Furthermore, we discover scenarios that significantly impact the effectiveness of the type regularizer.