Holographic Embeddings of Knowledge Graphs

16 Oct 2015  ·  Maximilian Nickel, Lorenzo Rosasco, Tomaso Poggio ·

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. read more

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Link Prediction FB15k HolE Hits@10 0.739 # 6
Hits@1 0.402 # 3
Hits@3 0.613 # 3
Link Prediction WN18 HolE Hits@10 0.949 # 16
Hits@3 0.945 # 11
Hits@1 0.93 # 15


No methods listed for this paper. Add relevant methods here