RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space

Sun, Zhiqing; Deng, Zhi-Hong; Nie, Jian-Yun; Tang, Jian

doi:10.48550/arxiv.1902.10197

Cited by 180 publications

(386 citation statements)

References 15 publications

Supporting

Mentioning

384

Contrasting

Order By: Relevance

“…authorship relations or citation links). In order to address this issue, the authors present a reimplementation of TransE [4] and RotatE [25] by using a newly proposed loss function optimized for many-to-many relations, i.e. Soft Margin (SM) Loss.…”

Section: Knowledge Graph Embeddings and Scholarly Datamentioning

confidence: 99%

A Knowledge Graph Embeddings based Approach for Author Name Disambiguation using Literals

Santini¹,

Gesese²,

Peroni³

et al. 2022

Preprint

View full text Add to dashboard Cite

Scholarly data is growing continuously containing information about the articles from plethora of venues including conferences, journals, etc. Many initiatives have been taken to make scholarly data available in the for of Knowledge Graphs (KGs). These efforts to standardize these data and make them accessible have also lead to many challenges such as exploration of scholarly articles, ambiguous authors, etc. This study more specifically targets the problem of Author Name Disambiguation (AND) on Scholarly KGs and presents a novel framework, Literally Author Name Disambiguation (LAND), which utilizes Knowledge Graph Embeddings (KGEs) using multimodal literal information generated from these KGs. This framework is based on three components: 1) Multimodal KGEs, 2) A blocking procedure, and finally, 3) Hierarchical Agglomerative Clustering. Extensive experiments have been conducted on two newly created KGs: (i) KG containing information from Scientometrics Journal from 1978 onwards (OC-782K), and (ii) a KG extracted from a well-known benchmark for AND provided by AMiner (AMiner-534K). The results show that our proposed architecture outperforms our baselines of 8-14% in terms of F 1 score and shows competitive performances on a challenging benchmark such as AMiner. The code and the datasets are publicly available through Github (https://github.com/sntcristian/and-kge) and Zenodo (https://zenodo.org/record/ 5675787#.YcCJzL3MJTY) respectively.

show abstract

Section: Knowledge Graph Embeddings and Scholarly Datamentioning

confidence: 99%

A Knowledge Graph Embeddings based Approach for Author Name Disambiguation using Literals

Santini¹,

Gesese²,

Peroni³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…We employ self-adversarial negative sampling [5] method to generate corrupt samples. We define the probability distribution of negative samples by:…”

Section: Loss Functionmentioning

confidence: 99%

“…We compared our model with several state-of-the-art baselines. For transformation based models, we compared our model to TransE [4], TorusE [24], RotatE [5] and HAKE [7]; for bilinear models, we compared our model to ComplEx [13], HolE [12], SimplE [9], DihEdral [14] and QuatE [6] (to make the comparison fair, we use the version of QuatE without type constraints on the common link prediction datasets considering the requirement of type constraints is too strong).…”

Section: Baselinesmentioning

confidence: 99%

“…Various models aiming at embedding entities and relations into lowdimension spaces have been proposed. For example, TransE [4] learned the embeddings of entities and relations by transforming head entity to tail entity according to the relation; RotatE [5] and QuatE [6] learned the embeddings of entities and relations by considering relations as rotations from head entities to tail entities. However, existing transformation based models fail to capture multiple relations between head and tail entities.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dual Quaternion Embeddings for Link Prediction

et al. 2021

View full text Add to dashboard Cite

The applications of knowledge graph have received much attention in the field of artificial intelligence. The quality of knowledge graphs is, however, often influenced by missing facts. To predict the missing facts, various solid transformation based models have been proposed by mapping knowledge graphs into low dimensional spaces. However, most of the existing transformation based approaches ignore that there are multiple relations between two entities, which is common in the real world. In order to address this challenge, we propose a novel approach called DualQuatE that maps entities and relations into a dual quaternion space. Specifically, entities are represented by pure quaternions and relations are modeled based on the combination of rotation and translation from head to tail entities. After that we utilize interactions of different translations and rotations to distinguish various relations between head and tail entities. Experimental results exhibit that the performance of DualQuatE is competitive compared to the existing state-of-the-art models.

show abstract

“…The key idea is to transform entities and relations in triple into continuous vector space. ComplEx [14] introduces complex embeddings so as to better model asymmetric relations and RotatE [13] further infers the composition pattern.…”

Section: Related Workmentioning

confidence: 99%

Improving Knowledge Graph Representation Learning by Structure Contextual Pre-training

Ye¹,

Zhang²,

Bi³

et al. 2021

Proceedings of the 10th International Joint Conference on Knowledge Graphs

View full text Add to dashboard Cite

Representation learning models for Knowledge Graphs (KG) have proven to be effective in encoding structural information and performing reasoning over KGs. In this paper, we propose a novel pre-training-then-fine-tuning framework for knowledge graph representation learning, in which a KG model is firstly pre-trained with triple classification task, followed by discriminative fine-tuning on specific downstream tasks such as entity type prediction and entity alignment. Drawing on the general ideas of learning deep contextualized word representations in typical pre-trained language models, we propose SCoP to learn pre-trained KG representations with structural and contextual triples of the target triple encoded. Experimental results demonstrate that fine-tuning SCoP not only outperforms results of baselines on a portfolio of downstream tasks but also avoids tedious task-specific model design and parameter training. CCS CONCEPTS• Computing methodologies → Artificial intelligence; Knowledge representation and reasoning.

show abstract

RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space

Cited by 180 publications

References 15 publications

A Knowledge Graph Embeddings based Approach for Author Name Disambiguation using Literals

A Knowledge Graph Embeddings based Approach for Author Name Disambiguation using Literals

Dual Quaternion Embeddings for Link Prediction

Improving Knowledge Graph Representation Learning by Structure Contextual Pre-training

Contact Info

Product

Resources

About