Knowledge Graph Embedding with Hierarchical Relation Structure

Zhang, Zhao; Zhuang, Fuzhen; Qu, Meng; Lin, Feng; He, Qing

doi:10.18653/v1/d18-1358

Cited by 59 publications

(32 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Later, Guo et al (2016) proposed KALE as a joint model that embeds the KG facts and the logical rules in a unified framework, by reusing the transnational assumption to model the facts and t-norm fuzzy logic to model the logical rules. Another rule-based KG embedding method, Hierarchical Relation Structure (HRS) (Zhang et al, 2018), which extends the existing KG embedding models TransE, TransH, and DistMult, to learn embedding by leveraging the rich information. According to HRS, the knowledge graph's relations conform to three layers: relation clusters, relations, and sub-relations, which can fit in the top, the middle, and the bottom layer of three-layer HRS, respectively.…”

Section: Distance-based Methodsmentioning

confidence: 99%

Application and evaluation of knowledge graph embeddings in biomedical data

Alshahrani

Thafar

Essack

2021

PeerJ Computer Science

View full text Add to dashboard Cite

Linked data and bio-ontologies enabling knowledge representation, standardization, and dissemination are an integral part of developing biological and biomedical databases. That is, linked data and bio-ontologies are employed in databases to maintain data integrity, data organization, and to empower search capabilities. However, linked data and bio-ontologies are more recently being used to represent information as multi-relational heterogeneous graphs, “knowledge graphs”. The reason being, entities and relations in the knowledge graph can be represented as embedding vectors in semantic space, and these embedding vectors have been used to predict relationships between entities. Such knowledge graph embedding methods provide a practical approach to data analytics and increase chances of building machine learning models with high prediction accuracy that can enhance decision support systems. Here, we present a comparative assessment and a standard benchmark for knowledge graph-based representation learning methods focused on the link prediction task for biological relations. We systematically investigated and compared state-of-the-art embedding methods based on the design settings used for training and evaluation. We further tested various strategies aimed at controlling the amount of information related to each relation in the knowledge graph and its effects on the final performance. We also assessed the quality of the knowledge graph features through clustering and visualization and employed several evaluation metrics to examine their uses and differences. Based on this systematic comparison and assessments, we identify and discuss the limitations of knowledge graph-based representation learning methods and suggest some guidelines for the development of more improved methods.

show abstract

Section: Distance-based Methodsmentioning

confidence: 99%

Application and evaluation of knowledge graph embeddings in biomedical data

Alshahrani

Thafar

Essack

2021

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…However, these works neglect rich correlations between relations. Relation structure (relational knowledge) has been studied and is quite effective for KG completion (Zhang et al, 2018b). To the best of our knowledge, this is the first effort to consider the relational knowledge of classes (relations) using KGs for RE.…”

Section: Related Workmentioning

confidence: 99%

Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks

Zhang

Deng

Sun

et al. 2019

Proceedings of the 2019 Conference of the North

200

View full text Add to dashboard Cite

We propose a distance supervised relation extraction approach for long-tailed, imbalanced data which is prevalent in real-world settings. Here, the challenge is to learn accurate "fewshot" models for classes existing at the tail of the class distribution, for which little data is available. Inspired by the rich semantic correlations between classes at the long tail and those at the head, we take advantage of the knowledge from data-rich classes at the head of the distribution to boost the performance of the data-poor classes at the tail. First, we propose to leverage implicit relational knowledge among class labels from knowledge graph embeddings and learn explicit relational knowledge using graph convolution networks. Second, we integrate that relational knowledge into relation extraction model by coarse-tofine knowledge-aware attention mechanism. We demonstrate our results for a large-scale benchmark dataset which show that our approach significantly outperforms other baselines, especially for long-tail relations.1

show abstract

“…[Lin et al, 2015a] presents PTransE, which encodes relation paths to embed both entities and relations in a lowdimensional space. [Zhang et al, 2018] proposes a threelayer structure of relations, which is merely an abstract structure obtained by gathering similar relations into clusters of relations and splitting coarse-grained relations into several finegrained sub-relations. Our RHS is a structure constructed by the generalization relationship named subRelationOf , which contains abundant semantic information.…”

Section: Kg Embedding With Multi-source Informationmentioning

confidence: 99%

“…TransE [Bordes et al, 2013] 89.2 68.4 TransH [Wang et al, 2014b] 86.8 73.8 TransR [Lin et al, 2015b] 85.6 66.9 TransD [Ji et al, 2015] 86.1 60.7 RotatE [Sun et al, 2019] 89.2 72.3 TransE-HRS [Zhang et al, 2018] 86.9 69.7 RESCAL [Nickel et al, 2011] 57.8 57.6 DistMult [Yang et al, 2015] 85.7 58.4 HolE [Nickel et al, 2016] 77.3 69.2 ComplEx [Trouillon et al, 2016] 86.3 74.6 SimplE [Kazemi and Poole, 2018] 86.5 67.6…”

Section: Modelmentioning

confidence: 99%

“…Unfortunately, the most existing translation-based representation learning methods merely focus on the structured information in triples, paying less attention to the rich information implied in RHS. [Zhang et al, 2018] suggests that relations in KGs conform to a three-layer structure, i.e., semantically similar relations can construct clusters of relations and coarse-grained relations can be further split into several fine-grained sub-relations. However, the structure mentioned in that paper is actually not a real RHS, which is simply obtained by a clustering algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

TransRHS: A Representation Learning Method for Knowledge Graphs with Relation Hierarchical Structure

Zhang

Wang

et al. 2020

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Representation learning of knowledge graphs aims to project both entities and relations as vectors in a continuous low-dimensional space. Relation Hierarchical Structure (RHS), which is constructed by a generalization relationship named subRelationOf between relations, can improve the overall performance of knowledge representation learning. However, most of the existing methods ignore this critical information, and a straightforward way of considering RHS may have a negative effect on the embeddings and thus reduce the model performance. In this paper, we propose a novel method named TransRHS, which is able to incorporate RHS seamlessly into the embeddings. More specifically, TransRHS encodes each relation as a vector together with a relation-specific sphere in the same space. Our TransRHS employs the relative positions among the vectors and spheres to model the subRelationOf, which embodies the inherent generalization relationships among relations. We evaluate our model on two typical tasks, i.e., link prediction and triple classification. The experimental results show that our TransRHS model significantly outperforms all baselines on both tasks, which verifies that the RHS information is significant to representation learning of knowledge graphs, and TransRHS can effectively and efficiently fuse RHS into knowledge graph embeddings.

show abstract

Knowledge Graph Embedding with Hierarchical Relation Structure

Cited by 59 publications

References 20 publications

Application and evaluation of knowledge graph embeddings in biomedical data

Application and evaluation of knowledge graph embeddings in biomedical data

Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks

TransRHS: A Representation Learning Method for Knowledge Graphs with Relation Hierarchical Structure

Contact Info

Product

Resources

About