Eintrag weiter verarbeiten
On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction
Gespeichert in:
| Zeitschriftentitel: | Journal of Artificial Intelligence and Soft Computing Research |
|---|---|
| Personen und Körperschaften: | , |
| In: | Journal of Artificial Intelligence and Soft Computing Research, 9, 2019, 1, S. 21-40 |
| Format: | E-Article |
| Sprache: | Englisch |
| veröffentlicht: |
Walter de Gruyter GmbH
|
| Schlagwörter: |
| author_facet |
Hou, Yuchen Holder, Lawrence B. Hou, Yuchen Holder, Lawrence B. |
|---|---|
| author |
Hou, Yuchen Holder, Lawrence B. |
| spellingShingle |
Hou, Yuchen Holder, Lawrence B. Journal of Artificial Intelligence and Soft Computing Research On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction Artificial Intelligence Computer Vision and Pattern Recognition Hardware and Architecture Modeling and Simulation Information Systems |
| author_sort |
hou, yuchen |
| spelling |
Hou, Yuchen Holder, Lawrence B. 2083-2567 Walter de Gruyter GmbH Artificial Intelligence Computer Vision and Pattern Recognition Hardware and Architecture Modeling and Simulation Information Systems http://dx.doi.org/10.2478/jaiscr-2018-0022 <jats:title>Abstract</jats:title> <jats:p>Deep learning has been successful in various domains including image recognition, speech recognition and natural language processing. However, the research on its application in graph mining is still in an early stage. Here we present Model R, a neural network model created to provide a deep learning approach to the link weight prediction problem. This model uses a node embedding technique that extracts node embeddings (knowledge of nodes) from the known links’ weights (relations between nodes) and uses this knowledge to predict the unknown links’ weights. We demonstrate the power of Model R through experiments and compare it with the stochastic block model and its derivatives. Model R shows that deep learning can be successfully applied to link weight prediction and it outperforms stochastic block model and its derivatives by up to 73% in terms of prediction accuracy. We analyze the node embeddings to confirm that closeness in embedding space correlates with stronger relationships as measured by the link weight. We anticipate this new approach will provide effective solutions to more graph mining tasks.</jats:p> On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction Journal of Artificial Intelligence and Soft Computing Research |
| doi_str_mv |
10.2478/jaiscr-2018-0022 |
| facet_avail |
Online |
| finc_class_facet |
Informatik Technik |
| format |
ElectronicArticle |
| fullrecord |
blob:ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMjQ3OC9qYWlzY3ItMjAxOC0wMDIy |
| id |
ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMjQ3OC9qYWlzY3ItMjAxOC0wMDIy |
| institution |
DE-D275 DE-Bn3 DE-Brt1 DE-Zwi2 DE-D161 DE-Gla1 DE-Zi4 DE-15 DE-Rs1 DE-Pl11 DE-105 DE-14 DE-Ch1 DE-L229 |
| imprint |
Walter de Gruyter GmbH, 2019 |
| imprint_str_mv |
Walter de Gruyter GmbH, 2019 |
| issn |
2083-2567 |
| issn_str_mv |
2083-2567 |
| language |
English |
| mega_collection |
Walter de Gruyter GmbH (CrossRef) |
| match_str |
hou2019ongraphminingwithdeeplearningintroducingmodelrforlinkweightprediction |
| publishDateSort |
2019 |
| publisher |
Walter de Gruyter GmbH |
| recordtype |
ai |
| record_format |
ai |
| series |
Journal of Artificial Intelligence and Soft Computing Research |
| source_id |
49 |
| title |
On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction |
| title_unstemmed |
On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction |
| title_full |
On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction |
| title_fullStr |
On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction |
| title_full_unstemmed |
On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction |
| title_short |
On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction |
| title_sort |
on graph mining with deep learning: introducing model r for link weight prediction |
| topic |
Artificial Intelligence Computer Vision and Pattern Recognition Hardware and Architecture Modeling and Simulation Information Systems |
| url |
http://dx.doi.org/10.2478/jaiscr-2018-0022 |
| publishDate |
2019 |
| physical |
21-40 |
| description |
<jats:title>Abstract</jats:title>
<jats:p>Deep learning has been successful in various domains including image recognition, speech recognition and natural language processing. However, the research on its application in graph mining is still in an early stage. Here we present Model R, a neural network model created to provide a deep learning approach to the link weight prediction problem. This model uses a node embedding technique that extracts node embeddings (knowledge of nodes) from the known links’ weights (relations between nodes) and uses this knowledge to predict the unknown links’ weights. We demonstrate the power of Model R through experiments and compare it with the stochastic block model and its derivatives. Model R shows that deep learning can be successfully applied to link weight prediction and it outperforms stochastic block model and its derivatives by up to 73% in terms of prediction accuracy. We analyze the node embeddings to confirm that closeness in embedding space correlates with stronger relationships as measured by the link weight. We anticipate this new approach will provide effective solutions to more graph mining tasks.</jats:p> |
| container_issue |
1 |
| container_start_page |
21 |
| container_title |
Journal of Artificial Intelligence and Soft Computing Research |
| container_volume |
9 |
| format_de105 |
Article, E-Article |
| format_de14 |
Article, E-Article |
| format_de15 |
Article, E-Article |
| format_de520 |
Article, E-Article |
| format_de540 |
Article, E-Article |
| format_dech1 |
Article, E-Article |
| format_ded117 |
Article, E-Article |
| format_degla1 |
E-Article |
| format_del152 |
Buch |
| format_del189 |
Article, E-Article |
| format_dezi4 |
Article |
| format_dezwi2 |
Article, E-Article |
| format_finc |
Article, E-Article |
| format_nrw |
Article, E-Article |
| _version_ |
1792330990945828865 |
| geogr_code |
not assigned |
| last_indexed |
2024-03-01T13:33:51.792Z |
| geogr_code_person |
not assigned |
| openURL |
url_ver=Z39.88-2004&ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fvufind.svn.sourceforge.net%3Agenerator&rft.title=On+Graph+Mining+With+Deep+Learning%3A+Introducing+Model+R+for+Link+Weight+Prediction&rft.date=2019-01-01&genre=article&issn=2083-2567&volume=9&issue=1&spage=21&epage=40&pages=21-40&jtitle=Journal+of+Artificial+Intelligence+and+Soft+Computing+Research&atitle=On+Graph+Mining+With+Deep+Learning%3A+Introducing+Model+R+for+Link+Weight+Prediction&aulast=Holder&aufirst=Lawrence+B.&rft_id=info%3Adoi%2F10.2478%2Fjaiscr-2018-0022&rft.language%5B0%5D=eng |
| SOLR | |
| _version_ | 1792330990945828865 |
| author | Hou, Yuchen, Holder, Lawrence B. |
| author_facet | Hou, Yuchen, Holder, Lawrence B., Hou, Yuchen, Holder, Lawrence B. |
| author_sort | hou, yuchen |
| container_issue | 1 |
| container_start_page | 21 |
| container_title | Journal of Artificial Intelligence and Soft Computing Research |
| container_volume | 9 |
| description | <jats:title>Abstract</jats:title> <jats:p>Deep learning has been successful in various domains including image recognition, speech recognition and natural language processing. However, the research on its application in graph mining is still in an early stage. Here we present Model R, a neural network model created to provide a deep learning approach to the link weight prediction problem. This model uses a node embedding technique that extracts node embeddings (knowledge of nodes) from the known links’ weights (relations between nodes) and uses this knowledge to predict the unknown links’ weights. We demonstrate the power of Model R through experiments and compare it with the stochastic block model and its derivatives. Model R shows that deep learning can be successfully applied to link weight prediction and it outperforms stochastic block model and its derivatives by up to 73% in terms of prediction accuracy. We analyze the node embeddings to confirm that closeness in embedding space correlates with stronger relationships as measured by the link weight. We anticipate this new approach will provide effective solutions to more graph mining tasks.</jats:p> |
| doi_str_mv | 10.2478/jaiscr-2018-0022 |
| facet_avail | Online |
| finc_class_facet | Informatik, Technik |
| format | ElectronicArticle |
| format_de105 | Article, E-Article |
| format_de14 | Article, E-Article |
| format_de15 | Article, E-Article |
| format_de520 | Article, E-Article |
| format_de540 | Article, E-Article |
| format_dech1 | Article, E-Article |
| format_ded117 | Article, E-Article |
| format_degla1 | E-Article |
| format_del152 | Buch |
| format_del189 | Article, E-Article |
| format_dezi4 | Article |
| format_dezwi2 | Article, E-Article |
| format_finc | Article, E-Article |
| format_nrw | Article, E-Article |
| geogr_code | not assigned |
| geogr_code_person | not assigned |
| id | ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMjQ3OC9qYWlzY3ItMjAxOC0wMDIy |
| imprint | Walter de Gruyter GmbH, 2019 |
| imprint_str_mv | Walter de Gruyter GmbH, 2019 |
| institution | DE-D275, DE-Bn3, DE-Brt1, DE-Zwi2, DE-D161, DE-Gla1, DE-Zi4, DE-15, DE-Rs1, DE-Pl11, DE-105, DE-14, DE-Ch1, DE-L229 |
| issn | 2083-2567 |
| issn_str_mv | 2083-2567 |
| language | English |
| last_indexed | 2024-03-01T13:33:51.792Z |
| match_str | hou2019ongraphminingwithdeeplearningintroducingmodelrforlinkweightprediction |
| mega_collection | Walter de Gruyter GmbH (CrossRef) |
| physical | 21-40 |
| publishDate | 2019 |
| publishDateSort | 2019 |
| publisher | Walter de Gruyter GmbH |
| record_format | ai |
| recordtype | ai |
| series | Journal of Artificial Intelligence and Soft Computing Research |
| source_id | 49 |
| spelling | Hou, Yuchen Holder, Lawrence B. 2083-2567 Walter de Gruyter GmbH Artificial Intelligence Computer Vision and Pattern Recognition Hardware and Architecture Modeling and Simulation Information Systems http://dx.doi.org/10.2478/jaiscr-2018-0022 <jats:title>Abstract</jats:title> <jats:p>Deep learning has been successful in various domains including image recognition, speech recognition and natural language processing. However, the research on its application in graph mining is still in an early stage. Here we present Model R, a neural network model created to provide a deep learning approach to the link weight prediction problem. This model uses a node embedding technique that extracts node embeddings (knowledge of nodes) from the known links’ weights (relations between nodes) and uses this knowledge to predict the unknown links’ weights. We demonstrate the power of Model R through experiments and compare it with the stochastic block model and its derivatives. Model R shows that deep learning can be successfully applied to link weight prediction and it outperforms stochastic block model and its derivatives by up to 73% in terms of prediction accuracy. We analyze the node embeddings to confirm that closeness in embedding space correlates with stronger relationships as measured by the link weight. We anticipate this new approach will provide effective solutions to more graph mining tasks.</jats:p> On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction Journal of Artificial Intelligence and Soft Computing Research |
| spellingShingle | Hou, Yuchen, Holder, Lawrence B., Journal of Artificial Intelligence and Soft Computing Research, On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction, Artificial Intelligence, Computer Vision and Pattern Recognition, Hardware and Architecture, Modeling and Simulation, Information Systems |
| title | On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction |
| title_full | On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction |
| title_fullStr | On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction |
| title_full_unstemmed | On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction |
| title_short | On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction |
| title_sort | on graph mining with deep learning: introducing model r for link weight prediction |
| title_unstemmed | On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction |
| topic | Artificial Intelligence, Computer Vision and Pattern Recognition, Hardware and Architecture, Modeling and Simulation, Information Systems |
| url | http://dx.doi.org/10.2478/jaiscr-2018-0022 |