Contrastive Predictive Embedding for learning and inference in knowledge graph

Knowledge graph embedding (KGE) aims to capture rich semantic information about entities and relationships in KGs, which is essential for Knowledge Graph Completion (KGC) and various downstream tasks. Existing KGE models differentiate between entity and relationship embeddings by constructing indirect pretext tasks and scoring functions to discern different types of triplets. In contrast, this paper introduces a novel KGE method called Contrastive Predictive Embedding (CPE), which dispenses with the need for defining scoring functions or negative sampling. Specifically, CPE directly predicts embeddings for unknown entities based on the known entity and relationship embeddings in triplets and compares them with the true embeddings. Additionally, this paper proposes a special optimization approach to enhance the performance of various Translation-based models. Experimental results on four benchmark KGs demonstrate that CPE improves the performance of original KGE models while maintaining lower computational complexity. On the FB15k-237 dataset, CPE enhances the MRR and $\text{Hit}@k(k\in \{1,3,10\})$ metrics of TransE by 1.55%, 3.37%, 4.58%, and 5.92%, respectively.