Filters








15,013 Hits in 4.2 sec

Benchmark and Best Practices for Biomedical Knowledge Graph Embeddings [article]

David Chang, Ivana Balazevic, Carl Allen, Daniel Chawla, Cynthia Brandt, Richard Andrew Taylor
2020 arXiv   pre-print
A recent family of models called knowledge graph embeddings have shown promising results on general domain knowledge graphs, and we explore their capabilities in the biomedical domain.  ...  We train several state-of-the-art knowledge graph embedding models on the SNOMED-CT knowledge graph, provide a benchmark with comparison to existing methods and in-depth discussion on best practices, and  ...  their advantages over previous methods, making a case for the importance of leveraging the multirelational nature of knowledge graphs for biomedical knowledge representation. • We establish a suite of  ... 
arXiv:2006.13774v1 fatcat:5ogiuwacnjfcpfctrurkaiiale

Benchmark and Best Practices for Biomedical Knowledge Graph Embeddings

David Chang, Ivana Balažević, Carl Allen, Daniel Chawla, Cynthia Brandt, Andrew Taylor
2020 Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing  
A recent family of models called knowledge graph embeddings have shown promising results on general domain knowledge graphs, and we explore their capabilities in the biomedical domain.  ...  We train several state-of-the-art knowledge graph embedding models on the SNOMED-CT knowledge graph, provide a benchmark with comparison to existing methods and in-depth discussion on best practices, and  ...  their advantages over previous methods, making a case for the importance of leveraging the multirelational nature of knowledge graphs for biomedical knowledge representation. • We establish a suite of  ... 
doi:10.18653/v1/2020.bionlp-1.18 pmid:33746351 pmcid:PMC7971091 fatcat:2qi6rl7rwjb7rlht34eqieau6e

Matching Entities Across Different Knowledge Graphs with Graph Embeddings [article]

Michael Azmy, Peng Shi, Jimmy Lin, Ihab F. Ilyas
2019 arXiv   pre-print
Using a classification-based approach, we find that a simple multi-layered perceptron based on representations derived from RDF2Vec graph embeddings of entities in each knowledge graph is sufficient to  ...  We formalize this problem and present two large-scale datasets for this task based on exiting cross-ontology links between DBpedia and Wikidata, focused on several hundred thousand ambiguous entities.  ...  Acknowledgments This research was supported by the Natural Sciences and Engineering Research Council (NSERC) of Canada.  ... 
arXiv:1903.06607v1 fatcat:la4z3lqvwndy7i3h6mbuozpvqy

Convolutional 2D Knowledge Graph Embeddings

Tim Dettmers, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel
2017 Zenodo  
To scale to large knowledge graphs and prevent overfitting due to over-parametrization, previous work seeks to reduce parameters by performing simple transformations in embedding space.  ...  We report state-of-the-art results for numerous previously introduced link prediction benchmarks, including the well-established FB15k and WN18 datasets.  ...  In this work we propose a neural link predictor, ConvE, that uses 2D convolution over embeddings to predict new links in knowledge graphs.  ... 
doi:10.5281/zenodo.833288 fatcat:lctoheg4zra4pmfiixkuzrvxpa

DSSLP: A Distributed Framework for Semi-supervised Link Prediction [article]

Dalong Zhang, Xianzheng Song, Ziqi Liu, Zhiqiang Zhang, Xin Huang, Lin Wang, Jun Zhou
2020 arXiv   pre-print
Experimental results demonstrate that the effectiveness and efficiency of DSSLP in serval public datasets as well as real-world datasets of industrial-scale graphs.  ...  However, it's a great challenge to train and deploy a link prediction model on industrial-scale graphs with billions of nodes and edges.  ...  As graph data exists ubiquitously, the link prediction problem has many applications, such as recommendation, fraud detection, knowledge graph completion, etc.  ... 
arXiv:2002.12056v2 fatcat:gw7ghj5ycjhn7ahscjuncb6bxq

Knowledge Embedding Based Graph Convolutional Network [article]

Donghan Yu, Yiming Yang, Ruohong Zhang, Yuexin Wu
2021 arXiv   pre-print
Experimental results on benchmark datasets show the advantageous performance of KE-GCN over strong baseline methods in the tasks of knowledge graph alignment and entity classification.  ...  propagation and the strengths of advanced knowledge embedding (a.k.a. knowledge graph embedding) methods, and goes beyond.  ...  This work is supported in part by the National Science Foundation (NSF) under grant IIS-1546329, and by the United States Department of Energy via the Brookhaven National Laboratory under Contract No.  ... 
arXiv:2006.07331v2 fatcat:lbbure7zsvhljdecmz6fssq6wi

Reasoning over RDF Knowledge Bases using Deep Learning [article]

Monireh Ebrahimi, Md Kamruzzaman Sarker, Federico Bianchi, Ning Xie, Derek Doran, Pascal Hitzler
2018 arXiv   pre-print
In this paper, we show that it is possible to train a Deep Learning system on RDF knowledge graphs, such that it is able to perform reasoning over new RDF knowledge graphs, with high precision and recall  ...  Semantic Web knowledge representation standards, and in particular RDF and OWL, often come endowed with a formal semantics which is considered to be of fundamental importance for the field.  ...  The Linked Data Cloud 1 website lists over 1,200 interlinked RDF(S) datasets, which constitute knowledge graphs suitable for our setting, some of which are of substantial size.  ... 
arXiv:1811.04132v1 fatcat:e42txhb2qvdsvj4bzuegxaxzvu

Inter-domain Multi-relational Link Prediction [article]

Luu Huu Phuc, Koh Takeuchi, Seiji Okajima, Arseny Tolmachev, Tomoyoshi Takebayashi, Koji Maruhashi, Hisashi Kashima
2021 arXiv   pre-print
Similar to other graph-structured data, link prediction is one of the most important tasks on multi-relational graphs and is often used for knowledge completion.  ...  However, this poses a real challenge to existing methods that are exclusively designed for link prediction between entities of the same graph only (intra-domain link prediction).  ...  of the art in various graph matching datasets.  ... 
arXiv:2106.06171v3 fatcat:mbpypirxwbhm5mokbluwquzpzm

Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings [article]

Ningyu Zhang, Xin Xie, Xiang Chen, Shumin Deng, Chuanqi Tan, Fei Huang, Xu Cheng, Huajun Chen
2022 arXiv   pre-print
In this paper, we propose kNN-KGE, a new knowledge graph embedding approach, by linearly interpolating its entity distribution with k-nearest neighbors.  ...  Previous knowledge graph embedding approaches usually map entities to representations and utilize score functions to predict the target entities, yet they struggle to reason rare or emerging unseen entities  ...  To the best of our knowledge, we are the first kNN-based approach for knowledge graph embedding.  ... 
arXiv:2201.05575v1 fatcat:umhtd3wp75h2doegoe7q3yd3ve

PNEL: Pointer Network based End-To-End Entity Linking over Knowledge Graphs [article]

Debayan Banerjee, Debanjan Chaudhuri, Mohnish Dubey, Jens Lehmann
2020 arXiv   pre-print
We demonstrate this in our evaluation over three datasets on the Wikidata Knowledge Graph.  ...  Question Answering systems are generally modelled as a pipeline consisting of a sequence of steps. In such a pipeline, Entity Linking (EL) is often the first step.  ...  Chris Biemann of the Language Technology Group, University of Hamburg, for his valuable suggestions towards improving this work.  ... 
arXiv:2009.00106v1 fatcat:ixskwok4rrcdbi2m3lngurzahi

Enhanced Temporal Knowledge Embeddings with Contextualized Language Representations [article]

Zhen Han, Ruotong Liao, Beiyan Liu, Yao Zhang, Zifeng Ding, Heinz Köppl, Hinrich Schütze, Volker Tresp
2022 arXiv   pre-print
ECOLA jointly optimizes the knowledge-text prediction objective and the temporal knowledge embeddings, which can simultaneously take full advantage of textual and knowledge information.  ...  Experimental results on the temporal knowledge graph completion task show that ECOLA outperforms state-of-the-art temporal KG models by a large margin.  ...  Implementation We use the datasets augmented with reciprocal relations to train all baseline models. We tune hyperparameters of our models using the random search and report the best configuration.  ... 
arXiv:2203.09590v2 fatcat:hb7nt2l5s5ejbjhgo5alcpz364

A Toolkit for Generating Code Knowledge Graphs [article]

Ibrahim Abdelaziz, Julian Dolby, Jamie McCusker, Kavitha Srinivas
2021 arXiv   pre-print
This results in an integrated code graph with over 2 billion triples.  ...  Knowledge graphs have been proven extremely useful in powering diverse applications in semantic search and natural language understanding.  ...  To our knowledge, Graph4Code is the first attempt to build a knowledge graph over a large repository of programs and systematically link it to documentation and forum posts related to code.  ... 
arXiv:2002.09440v3 fatcat:6m2xxc3xvrcvrhlykzqsr5rzqi

On event-driven knowledge graph completion in digital factories

Martin Ringsquandl, Evgeny Kharlamov, Daria Stepanova, Steffen Lamparter, Raffaello Lepratti, Ian Horrocks, Peer Kroger
2017 2017 IEEE International Conference on Big Data (Big Data)  
., in the form of knowledge graphs.  ...  Creation and maintenance of such knowledge is expensive and requires automation.  ...  ., at a mid size plant this knowledge may contain information about up to hundreds of machines, processes and materials, and hundreds of thousands of events.  ... 
doi:10.1109/bigdata.2017.8258105 dblp:conf/bigdataconf/RingsquandlKSLL17 fatcat:zsujquk2gve7fc4ut3463kqdbu

Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs [article]

Rakshit Trivedi, Hanjun Dai, Yichen Wang, Le Song
2017 arXiv   pre-print
Reasoning over time in such dynamic knowledge graphs is not yet well understood.  ...  The availability of large scale event data with time stamps has given rise to dynamically evolving knowledge graphs that contain temporal information for each edge.  ...  to enhancement of knowledge graph.  ... 
arXiv:1705.05742v3 fatcat:ipr7szsdkfc5bpbttttogllkpy

Benchmarking neural embeddings for link prediction in knowledge graphs under semantic and structural changes [article]

Asan Agibetov, Matthias Samwald
2020 arXiv   pre-print
We define relation-centric connectivity measures that allow us to connect the link prediction capacity to the structure of the knowledge graph.  ...  Recently, link prediction algorithms based on neural embeddings have gained tremendous popularity in the Semantic Web community, and are extensively used for knowledge graph completion.  ...  As such, the overall performance of specialized or generalized embeddings on one knowledge graph is characterized by these three distributions over all relations in the given knowledge graph.  ... 
arXiv:2005.07654v2 fatcat:iy273mqrofcn7fp3gtpahba65e
« Previous Showing results 1 — 15 out of 15,013 results