Enhancing Knowledge Graph Embedding with Probabilistic Negative Sampling

@article{Kanojia2017EnhancingKG,
  title={Enhancing Knowledge Graph Embedding with Probabilistic Negative Sampling},
  author={Vibhor Kanojia and Hideyuki Maeda and Riku Togashi and Sumio Fujita},
  journal={Proceedings of the 26th International Conference on World Wide Web Companion},
  year={2017}
}
Link Prediction using Knowledge graph embedding projects symbolic entities and relations into low dimensional vector space, thereby learning the semantic relations between entities. Among various embedding models, there is a series of translation-based models such as TransE[1], TransH[2], and TransR[3]. This paper proposes modifications in the TransR model to address the issue of skewed data which is common in real-world knowledge graphs. The enhancements enable the model to smartly generate… 

Figures and Tables from this paper

KNOWLEDGE GRAPH EMBEDDING
TLDR
This review summarizes current negative sampling approaches in KGE into three categories, static distribution-based, dynamic distribution- based and custom cluster-based respectively, and discusses the most prevalent existing approaches and their characteristics.
Translating Embeddings for Knowledge Graph Completion Utilizing Type Correlations
TLDR
This paper proposes a novel knowledge graph embedding method, able to take advantages of both fact triples and type information for entities, and assumes that if two entities are correlated according to their belonging types, embeddings should be closer to each other in the low-dimensional space.
A Birds Eye View on Knowledge Graph Embeddings, Software Libraries, Applications and Challenges
TLDR
Existing KGC approaches are discussed, including the state-of-the-art Knowledge Graph Embeddings (KGE), not only on static graphs but also for the latest trends such as multimodal, temporal, and uncertain knowledge graphs.
Dual Constrained Question Embeddings with Relational Knowledge Bases for Simple Question Answering
TLDR
A dual constraint model is proposed which exploits the embeddings obtained by Trans* family of algorithms to solve the simple QA problem without using any additional resources such as paraphrase datasets.
Knowledge Inference Model of OCR Conversion Error Rules Based on Chinese Character Construction Attributes Knowledge Graph
TLDR
Compared with the current mainstream knowledge inference model, the OCR conversion error rules inference model incorporating the feature cross algorithm has achieved important improvements in MRR, hits@1, Hits@2 and other evaluation indicators on public data sets and task-related data sets.
Statistical Analysis of Multi-Relational Network Recovery
In this paper, we develop asymptotic theories for a class of latent variable models for large-scale multi-relational networks. In particular, we establish consistency results and asymptotic error
Computer Science & Information Technology
TLDR
A unique fictional vehicle with tilt structure is put forward to help evaluate the property of the tilt-structure-aimed controllers and one phenomenon (state drift) in controlling an over-actuated tilt structure by feedback linearization is presented subsequently.

References

SHOWING 1-5 OF 5 REFERENCES
TransG : A Generative Model for Knowledge Graph Embedding
TLDR
This paper proposes a novel generative model (TransG) to address the issue of multiple relation semantics that a relation may have multiple meanings revealed by the entity pairs associated with the corresponding triples.
Translating Embeddings for Modeling Multi-relational Data
TLDR
TransE is proposed, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities, which proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases.
Learning Entity and Relation Embeddings for Knowledge Graph Completion
TLDR
TransR is proposed to build entity and relation embeddings in separate entity space and relation spaces to build translations between projected entities and to evaluate the models on three tasks including link prediction, triple classification and relational fact extraction.
Knowledge Graph Embedding by Translating on Hyperplanes
TLDR
This paper proposes TransH which models a relation as a hyperplane together with a translation operation on it and can well preserve the above mapping properties of relations with almost the same model complexity of TransE.
References
  • Medicine
  • 1971
TLDR
11. Brunck W: Die systematische untersuchung des sprachorgans bei angeborenen gaumendefekte ist wirklich ein wirkliches Problem gegen €” Pneumatisationsverhaitnisse bel gaumenspaltentragem.