Evidential relational-graph convolutional networks for entity classification in knowledge graphs

Weller, Tobias ; Paulheim, Heiko

[img] PDF
weller2021ergcn.pdf - Published

Download (1MB)

DOI: https://doi.org/10.1145/3459637.3482102
URL: https://madoc.bib.uni-mannheim.de/60876
Additional URL: https://dl.acm.org/doi/abs/10.1145/3459637.3482102
URN: urn:nbn:de:bsz:180-madoc-608768
Document Type: Conference or workshop publication
Year of publication: 2021
Book title: CIKM '21 : Proceedings of the 30th ACM International Conference on Information & Knowledge Management
Page range: 3533-3537
Conference title: CIKM '21
Location of the conference venue: Online
Date of the conference: 1.-5.11.2021
Publisher: Demartini, Gianluca ; Zuccon, Guido
Place of publication: New York, NY
Publishing house: Association for Computing Machinery
ISBN: 978-1-4503-8446-9
Publication language: English
Institution: School of Business Informatics and Mathematics > Data Science (Paulheim 2018-)
Pre-existing license: Creative Commons Attribution, Share Alike 4.0 International (CC BY-SA 4.0)
Subject: 004 Computer science, internet
Keywords (English): evidential learning , graph convolutional neural network , knowledge graph, entity classification
Abstract: Despite the vast amount of information encoded in knowledge graphs, they often remain incomplete. Neural networks, in particular Graph Convolutional Neural Networks, have been shown to be effective predictors to complete information about the class affiliation of entities in knowledge graphs. However, these models remain ignorant to their predictions confidence due to their used point estimate of a softmax output. In this paper, we combine Graph Convolutional Neural Networks with recent developments in the field of Evidential Learning by placing a Dirichlet distribution on the class probabilities to overcome this problem. We use the continuous output of a Graph Convolutional Neural Network as parameters for a Dirichlet distribution. In this way, the predictions of the model are represented as a distribution over possible softmax outputs, rather than a point estimate of a softmax output. The experiments show that a better performance in predicting class affiliations can be achieved compared to recent models. In addition, the experiments show that this approach overcomes the well-known problem of overconfident prediction of deterministic neural networks.
Additional information: Online-Ressource

Dieser Eintrag ist Teil der Universitätsbibliographie.

Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.

Metadata export


+ Search Authors in

BASE: Weller, Tobias ; Paulheim, Heiko

Google Scholar: Weller, Tobias ; Paulheim, Heiko

ORCID: Weller, Tobias ; Paulheim, Heiko ORCID: 0000-0003-4386-8195

+ Download Statistics

Downloads per month over past year

View more statistics

You have found an error? Please let us know about your desired correction here: E-Mail

Actions (login required)

Show item Show item