BuB: a builder-booster model for link prediction on knowledge graphs

Abstract

Abstract Link prediction (LP) has many applications in various fields. Much research has been carried out on the LP field, and one of the most critical problems in LP models is handling one-to-many and many-to-many relationships. To the best of our knowledge, there is no research on discriminative fine-tuning (DFT). DFT means having different learning rates for every parts of the model. We introduce the BuB model, which has two parts: relationship Builder and Relationship Booster. Relationship Builder is responsible for building the relationship, and Relationship Booster is responsible for strengthening the relationship. By writing the ranking function in polar coordinates and using the nth root, our proposed method provides solutions for handling one-to-many and many-to-many relationships and increases the optimal solutions space. We try to increase the importance of the Builder part by controlling the learning rate using the DFT concept. The experimental results show that the proposed method outperforms state-of-the-art methods on benchmark datasets.

Keywords

• Link prediction
• Knowledge graph completion
• BuB
• Relationship builder and booster
• Discriminative fine-tuning