Filters








121,473 Hits in 8.1 sec

Relation path embedding in knowledge graphs

Xixun Lin, Yanchun Liang, Fausto Giunchiglia, Xiaoyue Feng, Renchu Guan
2018 Neural computing & applications (Print)  
paths and propose a novel relation path embedding model named as RPE.  ...  They indicate that our model is capable of catching the semantics of relation paths, which is significant for knowledge representation learning.  ...  In this paper, we propose a novel relation path embedding model (RPE) to explicitly model knowledge graph by taking full advantage of the semantics of relation paths.  ... 
doi:10.1007/s00521-018-3384-6 fatcat:tebn6t3vobg2loyxxv2a3rpx6u

Knowledge Graph Embeddings [chapter]

Paolo Rosso, Dingqi Yang, Philippe Cudré-Mauroux
2018 Encyclopedia of Big Data Technologies  
Learning knowledge graph embeddings Learning KG embeddings consists in two key steps in general: 1.  ...  In a typical KG such as Freebase Bollacker et al (2008) or Google's Knowledge Graph Google (2014), entities are connected via relations. For example, Bern is capital of Switzerland.  ... 
doi:10.1007/978-3-319-63962-8_284-1 fatcat:xwmtv26vyrayvk3uwudy32xaz4

Retrofitting Distributional Embeddings to Knowledge Graphs with Functional Relations [article]

Benjamin J. Lengerich, Andrew L. Maas, Christopher Potts
2018 arXiv   pre-print
Methods for retrofitting pre-trained entity representations to the structure of a knowledge graph typically assume that entities are embedded in a connected space and that relations imply similarity.  ...  Knowledge graphs are a versatile framework to encode richly structured data relationships, but it can be challenging to combine these graphs with unstructured data.  ...  while the relation functions are learned.  ... 
arXiv:1708.00112v3 fatcat:z6bkghqgjbdaberikwyqvorf3u

PairRE: Knowledge Graph Embeddings via Paired Relation Vectors [article]

Linlin Chao, Jianshan He, Taifeng Wang, Wei Chu
2021 arXiv   pre-print
Distance based knowledge graph embedding methods show promising results on link prediction task, on which two topics have been widely studied: one is the ability to handle complex relations, such as N-to  ...  Moreover, We set a new state-of-the-art on two knowledge graph datasets of the challenging Open Graph Benchmark.  ...  The latter is learning and inferring relation patterns according to observed triples, as the success of knowledge graph completion heavily relies on this ability [3, 26] .  ... 
arXiv:2011.03798v3 fatcat:stgf3t2akjfx7p2c32ljr7fwea

Knowledge Graph Embedding with Hierarchical Relation Structure

Zhao Zhang, Fuzhen Zhuang, Meng Qu, Fen Lin, Qing He
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
Most existing researches are focusing on knowledge graph embedding (KGE) models.  ...  To this end, in this paper, we extend existing KGE models TransE, TransH and Dist-Mult, to learn knowledge representations by leveraging the information from the HRS.  ...  Introduction Knowledge Graphs (KGs) are extremely useful resources for many AI-related applications, such as question answering, information retrieval and query expansion.  ... 
doi:10.18653/v1/d18-1358 dblp:conf/emnlp/ZhangZQLH18 fatcat:u7m2hkpi5na7fcpwwmonlln5ru

Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding [article]

Yun Tang, Jing Huang, Guangtao Wang, Xiaodong He, Bowen Zhou
2020 arXiv   pre-print
Translational distance-based knowledge graph embedding has shown progressive improvements on the link prediction task, from TransE to the latest state-of-the-art RotatE.  ...  The proposed method includes two-folds, first we extend the RotatE from 2D complex domain to high dimension space with orthogonal transforms to model relations for better modeling capacity.  ...  On WN18RR our results achieve the new state-of-the-art performance. 2 Related work Knowledge Graph Embedding Knowledge graph embedding could be roughly categorized into two classes : distance-based models  ... 
arXiv:1911.04910v3 fatcat:iuhb7wxduzbqlkiil3r6w3lpci

Knowledge Graph Embedding with Multiple Relation Projections [article]

Kien Do, Truyen Tran, Svetha Venkatesh
2018 arXiv   pre-print
Knowledge graphs contain rich relational structures of the world, and thus complement data-driven machine learning in heterogeneous data.  ...  However, state-of-the-art relation projection methods such as TransR, TransD or TransSparse do not model the correlation between relations, and thus are not scalable to complex knowledge graphs with thousands  ...  Holographic Embedding (HolE) [19] , a novel method leveraging the holographic models of associative memory to learn the compositional representations of knowledge graphs.  ... 
arXiv:1801.08641v1 fatcat:tksyzqblknbifn4nmyoyb6etwq

Interpreting Knowledge Graph Relation Representation from Word Embeddings [article]

Carl Allen, Ivana Balažević, Timothy Hospedales
2021 arXiv   pre-print
Many models learn representations of knowledge graph data by exploiting its low-rank latent structure, encoding known relations between entities and enabling unknown facts to be inferred.  ...  We show that empirical properties of relation representations and the relative performance of leading knowledge graph representation methods are justified by our analysis.  ...  of different knowledge graph models for each relation type.  ... 
arXiv:1909.11611v2 fatcat:ddgefluk3zfchoz5t4joxr754y

TranS: Transition-based Knowledge Graph Embedding with Synthetic Relation Representation [article]

Xuanyu Zhang, Qing Yang, Dongliang Xu
2022 arXiv   pre-print
Knowledge graph embedding (KGE) aims to learn continuous vectors of relations and entities in knowledge graph.  ...  In this paper, we propose a novel transition-based method, TranS, for knowledge graph embedding.  ...  Conclusion In this paper, we propose a novel transition-based knowledge graph embedding model, TranS, to solve the issues of complex relations, especially the situation of same entity pair with different  ... 
arXiv:2204.08401v2 fatcat:n6zeh4dwtjcfvl6cmqt5mmeshe

Knowledge Embedding Based Graph Convolutional Network [article]

Donghan Yu, Yiming Yang, Ruohong Zhang, Yuexin Wu
2021 arXiv   pre-print
propagation and the strengths of advanced knowledge embedding (a.k.a. knowledge graph embedding) methods, and goes beyond.  ...  Most GCN methods are either restricted to graphs with a homogeneous type of edges (e.g., citation links only), or focusing on representation learning for nodes only instead of jointly propagating and updating  ...  Especially, in order to capture the rich semantics of heterogeneous relations in knowledge graphs, both entity embeddings and relation embeddings in our model are used to enforce optimization of each other  ... 
arXiv:2006.07331v2 fatcat:lbbure7zsvhljdecmz6fssq6wi

QuatRE: Relation-Aware Quaternions for Knowledge Graph Embeddings [article]

Dai Quoc Nguyen and Thanh Vu and Tu Dinh Nguyen and Dinh Phung
2022 arXiv   pre-print
We propose a simple yet effective embedding model to learn quaternion embeddings for entities and relations in knowledge graphs.  ...  The model achieves this goal by further associating each relation with two relation-aware rotations, which are used to rotate quaternion embeddings of the head and tail entities, respectively.  ...  CONCLUSION In this paper, we propose QuatRE -a simple yet effective knowledge graph embedding model -to learn the embeddings of entities and relations within the Quaternion space with the Hamilton product  ... 
arXiv:2009.12517v2 fatcat:alpth2t7cvhepibmqnrgddlpme

Embedding Uncertain Knowledge Graphs [article]

Xuelu Chen, Muhao Chen, Weijia Shi, Yizhou Sun, Carlo Zaniolo
2019 arXiv   pre-print
However, there are many KGs that model uncertain knowledge, which typically model the inherent uncertainty of relations facts with a confidence score, and embedding such uncertain knowledge represents  ...  Embedding models for deterministic Knowledge Graphs (KG) have been extensively studied, with the purpose of capturing latent semantic relations between entities and incorporating the structured knowledge  ...  Uncertain Knowledge Graph Embedding Problem.  ... 
arXiv:1811.10667v2 fatcat:joig6esu7jgqvfgnys3grohxt4

Embedding Uncertain Knowledge Graphs

Xuelu Chen, Muhao Chen, Weijia Shi, Yizhou Sun, Carlo Zaniolo
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Embedding models for deterministic Knowledge Graphs (KG) have been extensively studied, with the purpose of capturing latent semantic relations between entities and incorporating the structured knowledge  ...  However, there are many KGs that model uncertain knowledge, which typically model the inherent uncertainty of relations facts with a confidence score, and embedding such uncertain knowledge represents  ...  Uncertain Knowledge Graph Embedding Problem.  ... 
doi:10.1609/aaai.v33i01.33013363 fatcat:vqxhhyj3e5cfli5thjehdld5ga

Federated Knowledge Graphs Embedding [article]

Hao Peng, Haoran Li, Yangqiu Song, Vincent Zheng, Jianxin Li
2021 arXiv   pre-print
In this paper, we propose a novel decentralized scalable learning framework, Federated Knowledge Graphs Embedding (FKGE), where embeddings from different knowledge graphs can be learnt in an asynchronous  ...  FKGE exploits adversarial generation between pairs of knowledge graphs to translate identical entities and relations of different domains into near embedding spaces.  ...  RELATED WORK As our work is closely related to federated learning and knowledge graph embedding, the related works are two-fold.  ... 
arXiv:2105.07615v1 fatcat:il5oopbv65cuzhtyk4ciyqr74u

Relation Embedding with Dihedral Group in Knowledge Graph

Canran Xu, Ruijiang Li
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
To fulfill this gap, we propose a new model called DihEdral, named after dihedral symmetry group. This new model learns knowledge graph embeddings that can capture relation compositions by nature.  ...  Link prediction is critical for the application of incomplete knowledge graph (KG) in the downstream tasks.  ...  composition are coherent with the relation embeddings learned from DihEdral.  ... 
doi:10.18653/v1/p19-1026 dblp:conf/acl/XuL19 fatcat:ekc67addibfkrliycybjsuqk24
« Previous Showing results 1 — 15 out of 121,473 results