# Knowledge Graph Fact Prediction via Knowledge-Enriched Tensor Factorization

arXiv: https://arxiv.org/abs/1902.03077 · HTML: https://mlsanity.com/paper/1902.03077/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2019.

## Built on by (most cited first, 3 of 3)

- [ER: Equivariance Regularizer for Knowledge Graph Completion](https://mlsanity.com/paper/2206.12142/) (2022)
- [Graph Learning Indexer: A Contributor-Friendly and Metadata-Rich Platform for Graph Learning Benchmarks](https://mlsanity.com/paper/2212.04537/) (2022)
- [A Knowledge Enhanced Learning and Semantic Composition Model for Multi-Claim Fact Checking](https://mlsanity.com/paper/2104.13046/) (2021)

## Abstract (arXiv)

We present a family of novel methods for embedding knowledge graphs into real-valued tensors. These tensor-based embeddings capture the ordered relations that are typical in the knowledge graphs represented by semantic web languages like RDF. Unlike many previous models, our methods can easily use prior background knowledge provided by users or extracted automatically from existing knowledge graphs. In addition to providing more robust methods for knowledge graph embedding, we provide a provably-convergent, linear tensor factorization algorithm. We demonstrate the efficacy of our models for the task of predicting new facts across eight different knowledge graphs, achieving between 5% and 50% relative improvement over existing state-of-the-art knowledge graph embedding techniques. Our empirical evaluation shows that all of the tensor decomposition models perform well when the average degree of an entity in a graph is high, with constraint-based models doing better on graphs with a small number of highly similar relations and regularization-based models dominating for graphs with relations of varying degrees of similarity.