Knowledge Graph Completion via Complex Tensor Factorization

22 Feb 2017Théo TrouillonChristopher R. DanceJohannes WelblSebastian RiedelÉric GaussierGuillaume Bouchard

In statistical relational learning, knowledge graph completion deals with automatically understanding the structure of large knowledge graphs---labeled directed graphs---and predicting missing relationships---labeled edges. State-of-the-art embedding models propose different trade-offs between modeling expressiveness, and time and space complexity... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Knowledge Graphs FB15k COMPLEX MRR 0.587 # 1
Link Prediction FB15k Complex MRR 0.692 # 6
Link Prediction FB15k Complex [email protected] 0.840 # 5
Link Prediction FB15k Complex [email protected] 0.759 # 5
Link Prediction FB15k Complex [email protected] 0.599 # 6