Holographic Embeddings of Knowledge Graphs
This work addresses the challenge of efficiently representing relational data like knowledge graphs for machine learning applications, offering a scalable solution with improved performance.
The authors tackled the problem of learning embeddings for knowledge graphs by proposing holographic embeddings (HolE), which use circular correlation to create compositional representations, and demonstrated that HolE outperforms state-of-the-art methods on link prediction tasks.
Learning embeddings of entities and relations is an efficient and versatile method to perform machine learning on relational data such as knowledge graphs. In this work, we propose holographic embeddings (HolE) to learn compositional vector space representations of entire knowledge graphs. The proposed method is related to holographic models of associative memory in that it employs circular correlation to create compositional representations. By using correlation as the compositional operator HolE can capture rich interactions but simultaneously remains efficient to compute, easy to train, and scalable to very large datasets. In extensive experiments we show that holographic embeddings are able to outperform state-of-the-art methods for link prediction in knowledge graphs and relational learning benchmark datasets.