Learning an Optimized Deep Neural Network for Link Prediction on Knowledge Graphs

W.X. Wilcke

Learning an Optimized Deep Neural Network for Link Prediction on Knowledge Graphs

Research output: Contribution to Conference › Poster › Academic

46 Downloads (Pure)

Abstract

Recent years have seen the emergence of graph-based Knowledge Bases build upon
Semantic Web technologies, known as Knowledge Graphs. Effectively learning from
these complex relational structures remains a challenge yet to be overcome.
Knowledge Graphs For this purpose, we are investigating the effectiveness of Link Prediction through
means of Deep Learning an Artificial Neural Network, as well to optimize both
learning method and model through Bayesian Hyper-parameter optimization.
Moreover, during evaluation, special attention will be given to the usefulness of made

Original language	English
Publication status	Published - 2015
Event	ECML PKDD - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases - Porto, Portugal Duration: 7 Sept 2015 → 11 Sept 2015 http://www.ecmlpkdd2015.org/

Conference

Conference	ECML PKDD - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
Abbreviated title	ECML
Country/Territory	Portugal
City	Porto
Period	7/09/15 → 11/09/15
Internet address	http://www.ecmlpkdd2015.org/

Keywords

Knowledge Graphs
Deep Learning

Access to Document

ecmlpkdd15posterFinal published version, 1.92 MBLicence: CC BY-SA

Persistent URL (handle)

Persistent link

1 Conference contribution

Learning an Optimized Deep Neural Network for Link Prediction on Knowledge Graphs
Wilcke, W. X., 2015, Proceedings of the ECMLPKDD 2015 Doctoral Consortium. Hollmén, J. & Papapetrou, P. (eds.). Helsinki: Aalto University, p. 226-235
Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

Cite this

@conference{8fe29e87845043f5bee8c5a2ce11a7c3,

title = "Learning an Optimized Deep Neural Network for Link Prediction on Knowledge Graphs",

abstract = "Recent years have seen the emergence of graph-based Knowledge Bases build upon Semantic Web technologies, known as Knowledge Graphs. Effectively learning from these complex relational structures remains a challenge yet to be overcome. Knowledge Graphs For this purpose, we are investigating the effectiveness of Link Prediction through means of Deep Learning an Artificial Neural Network, as well to optimize both learning method and model through Bayesian Hyper-parameter optimization. Moreover, during evaluation, special attention will be given to the usefulness of made ",

keywords = "Knowledge Graphs, Deep Learning",

author = "W.X. Wilcke",

year = "2015",

language = "English",

note = "ECML PKDD - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML ; Conference date: 07-09-2015 Through 11-09-2015",

url = "http://www.ecmlpkdd2015.org/",

}

TY - CONF

T1 - Learning an Optimized Deep Neural Network for Link Prediction on Knowledge Graphs

AU - Wilcke, W.X.

PY - 2015

Y1 - 2015

N2 - Recent years have seen the emergence of graph-based Knowledge Bases build upon Semantic Web technologies, known as Knowledge Graphs. Effectively learning from these complex relational structures remains a challenge yet to be overcome. Knowledge Graphs For this purpose, we are investigating the effectiveness of Link Prediction through means of Deep Learning an Artificial Neural Network, as well to optimize both learning method and model through Bayesian Hyper-parameter optimization. Moreover, during evaluation, special attention will be given to the usefulness of made

AB - Recent years have seen the emergence of graph-based Knowledge Bases build upon Semantic Web technologies, known as Knowledge Graphs. Effectively learning from these complex relational structures remains a challenge yet to be overcome. Knowledge Graphs For this purpose, we are investigating the effectiveness of Link Prediction through means of Deep Learning an Artificial Neural Network, as well to optimize both learning method and model through Bayesian Hyper-parameter optimization. Moreover, during evaluation, special attention will be given to the usefulness of made

KW - Knowledge Graphs

KW - Deep Learning

M3 - Poster

T2 - ECML PKDD - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases

Y2 - 7 September 2015 through 11 September 2015

ER -

Learning an Optimized Deep Neural Network for Link Prediction on Knowledge Graphs

Abstract

Conference

Keywords

Access to Document

Persistent URL (handle)

Fingerprint

Research output

Learning an Optimized Deep Neural Network for Link Prediction on Knowledge Graphs

Cite this