Context-Dependent Knowledge Graph Embedding

By Yuanfei Luo, Quan Wang, Li Guo. 2015

53 citations recorded by the source corpus.

We consider the problem of embedding knowledge graphs (KGs) into continuous vector spaces. Existing methods can only deal with explicit relationships within each triple, i.e., local connectivity patterns, but cannot handle implicit relationships across different triples, i.e., contextual connectivity patterns. This paper proposes context-dependent KG embedding, a twostage scheme that takes into account both types of connectivity patterns and obtains more accurate embeddings. We evaluate our approach on the tasks of link prediction and triple classification, and achieve significant and consistent improvements over state-of-the-art methods.

Subfields: Artificial Intelligence, Molecular Biology, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Vincent Wenchen Zheng
2. Kevin Chen-Chuan Chang
3. Zhou Zhao
4. Bryan Perozzi
5. Hongyun Cai
6. Zemin Liu
7. Sami Abu-El-Haija
8. Jing Ying

In Molecular Biology

1. Alexander A. Alemi
2. Rami Al-Rfou
3. Sami Abu-El-Haija
4. Hongyun Cai
5. Quan Wang
6. Kevin Chen-Chuan Chang
7. Dinh Q. Phung
8. Zemin Liu

In Statistical and Nonlinear Physics

1. Kevin Chen-Chuan Chang
2. Vincent Wenchen Zheng
3. Zemin Liu
4. Alexander A. Alemi
5. Rami Al-Rfou
6. Sami Abu-El-Haija
7. Hongyun Cai
8. Quan Wang

Citations in the corpus

• A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, background): “Triplet classification [14], [15], [38], [51], [52], [53], [61], [142] is a specific application for knowledge graph.”
• A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network (2017, background): “tities in the KBs could help to get contextual information for improving KB completion performance (Lin et al., 2015a; Luo et al., 2015; Guu et al., 2015; Toutanova et al., 2016; Nguyen et al., 2016a).”
• Knowledge Graph Embedding: A Survey of Approaches and Applications (2017, background): “2 considers only relations in a path, while path context further takes into account intermediate nodes in that path, as practiced in [29], [100], [120].”
• Semantic Proximity Search on Heterogeneous Graph by Proximity Embedding (2017, background): “Very few works attempt to learn embedding for more than one node (Luo et al. 2015; Zheng et al. 2016), and they are not for proximity search.”
• Watch Your Step: Learning Node Embeddings via Graph Attention (2017, background): “These embeddings have demonstrated outstanding performance on a number of tasks including node classification [29, 15], knowledge-base completion [24], semi-supervised learning [37], and link prediction [2].”