555 Hits in 6.5 sec

A Birds Eye View on Knowledge Graph Embeddings, Software Libraries, Applications and Challenges [article]

Satvik Garg, Dwaipayan Roy
2022 arXiv   pre-print
knowledge graphs.  ...  In addition, reinforcement learning techniques are reviewed to model complex queries as a link prediction problem.  ...  Scalability Scalability is imperative in a large-scope knowledge graph.  ... 
arXiv:2205.09088v1 fatcat:c4gfzg4ldras3axpf5wvbldstm

A Review of Relational Machine Learning for Knowledge Graphs

Maximilian Nickel, Kevin Murphy, Volker Tresp, Evgeniy Gabrilovich
2016 Proceedings of the IEEE  
In this paper, we provide a review of how such statistical models can be "trained" on large knowledge graphs, and then used to predict new facts about the world (which is equivalent to predicting new edges  ...  Finally, we discuss how such statistical models of graphs can be combined with text-based information extraction methods for automatically constructing knowledge graphs from the Web.  ...  In the context of knowledge graphs, link prediction is also referred to as knowledge graph completion.  ... 
doi:10.1109/jproc.2015.2483592 fatcat:uk6xvh5xljgf7aytfadzwzncsi

Non-Parametric Estimation of Multiple Embeddings for Link Prediction on Dynamic Knowledge Graphs

Yi Tay, Anh Luu, Siu Cheung Hui
Our experimental results show that our proposed approach outperforms TransE and many other embedding methods for link prediction on knowledge graphs on both public benchmark dataset and a real world dynamic  ...  Knowledge graphs play a significant role in many intelligent systems such as semantic search and recommendation systems.  ...  Lastly, we introduce how puTransE is able to handle dynamic knowledge graphs. Proposed Architecture for Online Link Prediction Figure 2 shows the proposed architecture for Online Link Prediction.  ... 
doi:10.1609/aaai.v31i1.10685 fatcat:eafya36yw5cftaveaghmlmwi2q

Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion [article]

Hung Nghiep Tran, Atsuhiro Takasu
2020 arXiv   pre-print
Knowledge graph completion is an important task that aims to predict the missing relational link between entities.  ...  cost, learn the interaction mechanisms from data automatically, and achieve state-of-the-art performance on the link prediction task.  ...  Knowledge graph completion, or link prediction, is a task that aims to predict new triples based on existing triples.  ... 
arXiv:2006.16365v1 fatcat:65us5hjslzb3dgx4vtpsvz7tb4

Predicting Potential Drug Targets Using Tensor Factorisation and Knowledge Graph Embeddings [article]

Cheng Ye, Rowan Swiers, Stephen Bonner, Ian Barrett
2021 arXiv   pre-print
We enriched the data with gene representations learned from a drug discovery-oriented knowledge graph and applied our proposed method to predict the clinical outcomes for unseen target and dis-ease pairs  ...  The result shows that incorporating knowledge graph embeddings significantly improves the prediction accuracy and that training tensor factorisation alongside a dense neural network outperforms other methods  ...  ACKNOWLEDGMENTS The authors would like to thank Ufuk Kirik, Manasa Ramakrishna, Natalja Kurbatova, Elizaveta Semenova and Claus Bendtsen for help and feedback throughout the preparation of this manuscript  ... 
arXiv:2105.10578v2 fatcat:ez2hakthnndjvb5ksi6cku5ycq

2021 Index IEEE Transactions on Knowledge and Data Engineering Vol. 33

2022 IEEE Transactions on Knowledge and Data Engineering  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TKDE Oct. 2021 3438-3452 Structured Graph Reconstruction for Scalable Clustering.  ...  Wu, J., +, TKDE May 2021 1831-1847 Structured Graph Reconstruction for Scalable Clustering.  ... 
doi:10.1109/tkde.2021.3128365 fatcat:4m5kefreyrbhpb3lhzvgqzm3qu

Type Prediction in Noisy RDF Knowledge Bases Using Hierarchical Multilabel Classification with Graph and Latent Features

Andre Melo, Johanna Völker, Heiko Paulheim
2017 International journal on artificial intelligence tools  
We show that the approach outperforms the current state of the art approaches for type prediction in SW knowledge bases, and does so in a more scalable way than existing algorithms for hierarchical multi-label  ...  However, it has never been viewed like that -to the best of our knowledge, all machine learning based methods for type prediction in SW knowledge bases proposed so far flatten the problem to non-hierarchical  ...  Graphs on the Web).  ... 
doi:10.1142/s0218213017600119 fatcat:mv3xo2pfszhfbf6bf6mqjbfnye

A Critical Review On Predicting Drug-Drug Reactions Using Machine Learning Techniques

A. Saran Kumar, Bannari Amman Institute of Technology, Sathyamangalam
2021 International Journal of Computational & Neural Engineering  
Many computational techniques have been used to predict the adverse effects of drug-drug interactions. However, these methods do not provide adequate information required for the prediction of DDI.  ...  Machine learning algorithms provide a set of methods which can increase the accuracy and success rate for well-defined issues with abundant data.  ...  Several similarity measures between all categories of drugs are calculated using knowledge graph in a scalable and distributed environment.  ... 
doi:10.19070/2572-7389-2100015 fatcat:fdckhboqpbhyzhrfyjhlckr7sa

A A Survey of the Link Prediction on Static and Temporal Knowledge Graph

Thanh Le, Hoang Nguyen, Bac Le
2021 Research and Development on Information and Communication Technology  
Link prediction in knowledge graphs gradually plays an essential role in the field of research and application.  ...  Finally, from the overview of the link prediction problem, we propose some directions to improve the models for future studies.  ...  Graph Embedding Based Models a) Tensor Decomposition Models of this group consider link prediction as a tensor decomposition task by converting knowledge graph to a 3D adjacency matrix or a 3D tensor.  ... 
doi:10.32913/mic-ict-research.v2021.n2.972 fatcat:vuvve5rzsbfgzpz5ax3sbqqxli

Distributed non-negative RESCAL with Automatic Model Selection for Exascale Data [article]

Manish Bhattarai, Namita Kharat, Erik Skau, Benjamin Nebgen, Hristo Djidjev, Sanjay Rajopadhye, James P. Smith, Boian Alexandrov
2022 arXiv   pre-print
Relational data usually contain triples, (subject, relation, object), and are represented as graphs/multigraphs, called knowledge graphs, which need to be embedded into a low-dimensional dense vector space  ...  Finally, pyDRESCALk determines the number of latent communities in an 11-terabyte dense and 9-exabyte sparse synthetic tensor.  ...  graph, X , we create an ensemble of r random tensors, [X q ] q=1,...  ... 
arXiv:2202.09512v1 fatcat:pe334e2pqnduhgpsmhgpsbcphe

Convolutional Hypercomplex Embeddings for Link Prediction [article]

Caglar Demir, Diego Moussallem, Stefan Heindorf, Axel-Cyrille Ngonga Ngomo
2021 arXiv   pre-print
In addition, models based on convolutions on real-valued embeddings often yield state-of-the-art results for link prediction.  ...  Knowledge graph embedding research has mainly focused on the two smallest normed division algebras, ℝ and ℂ.  ...  We are grateful to Pamela Heidi Douglas for proofreading the manuscript.  ... 
arXiv:2106.15230v2 fatcat:phiv2jebo5h2zb7uflt4r6l5lu

Temporal Link Prediction Using Matrix and Tensor Factorizations

Daniel M. Dunlavy, Tamara G. Kolda, Evrim Acar
2011 ACM Transactions on Knowledge Discovery from Data  
In this paper, we consider bipartite graphs that evolve over time and consider matrix- and tensor-based methods for predicting future links.  ...  We show how the well-known Katz method for link prediction can be extended to bipartite graphs and, moreover, approximated in a scalable way using a truncated singular value decomposition.  ...  We consider both matrix-and tensor-based methods for link prediction.  ... 
doi:10.1145/1921632.1921636 fatcat:t47lqg2nxraehn2dwg6w4hr2xu

Link Prediction in Social Networks: the State-of-the-Art [article]

Peng Wang and Baowen Xu and Yurong Wu and Xiaoyu Zhou
2014 arXiv   pre-print
A systematical category for link prediction techniques and problems is presented. Then link prediction techniques and problems are analyzed and discussed.  ...  In social networks, link prediction predicts missing links in current networks and new or dissolution links in future networks, is important for mining and analyzing the evolution of social networks.  ...  Link Prediction Scalability The scalability and effectiveness are both important for massive real world social networks.  ... 
arXiv:1411.5118v2 fatcat:ns5ufekku5hwnotjlfgj2oiaei

Link prediction in social networks: the state-of-the-art

Peng Wang, BaoWen Xu, YuRong Wu, XiaoYu Zhou
2014 Science China Information Sciences  
A systematical category for link prediction techniques and problems is presented. Then link prediction techniques and problems are analyzed and discussed.  ...  In social networks, link prediction predicts missing links in current networks and new or dissolution links in future networks, is important for mining and analyzing the evolution of social networks.  ...  Link prediction scalability The scalability and effectiveness are both important for massive real world social networks. Sarkar et al.  ... 
doi:10.1007/s11432-014-5237-y fatcat:x6jd4zwg7fgefjrho4en4rtfgm

MARINE: Multi-relational Network Embeddings with Relational Proximity and Node Attributes

Noriaki Kawamae
2019 The World Wide Web Conference on - WWW '19  
We also extend the framework to incorporate existing features of nodes in a graph, which can further be exploited for the ensemble of embedding.  ...  We observe that there are two diverse branches of network embedding: for homogeneous graphs and for multi-relational graphs.  ...  Random Forest Regressor (number of estimators = 32) is used to train on embeddings for prediction.  ... 
doi:10.1145/3308558.3313715 dblp:conf/www/Kawamae19 fatcat:mt5o5joidvgapgmf4lain3t3be
« Previous Showing results 1 — 15 out of 555 results