On Joint Representation Learning of Network Structure and Document Content
J. Schlötterer, C. Seifert, and M. Granitzer. Machine Learning and Knowledge Extraction, page 237--251. Cham, Springer International Publishing, (2017)
Abstract
Inspired by the advancements of representation learning for natural language processing, learning continuous feature representations of nodes in networks has recently gained attention. Similar to word embeddings, node embeddings have been shown to capture certain semantics of the network structure. Combining both research directions into a joint representation learning of network structure and document content seems a promising direction to increase the quality of the learned representations. However, research is typically focused on either word or network embeddings and few approaches that learn a joint representation have been proposed. We present an overview of that field, starting at word representations, moving over document and network node representations to joint representations. We make the connections between the different models explicit and introduce a novel model for learning a joint representation. We present different methods for the novel model and compare the presented approaches in an evaluation. This paper explains how the different models recently proposed in the literature relate to each other and compares their performance.
Description
On Joint Representation Learning of Network Structure and Document Content | SpringerLink
%0 Conference Paper
%1 10.1007/978-3-319-66808-6_16
%A Schlötterer, Jörg
%A Seifert, Christin
%A Granitzer, Michael
%B Machine Learning and Knowledge Extraction
%C Cham
%D 2017
%E Holzinger, Andreas
%E Kieseberg, Peter
%E Tjoa, A Min
%E Weippl, Edgar
%I Springer International Publishing
%K content network structure web
%P 237--251
%T On Joint Representation Learning of Network Structure and Document Content
%X Inspired by the advancements of representation learning for natural language processing, learning continuous feature representations of nodes in networks has recently gained attention. Similar to word embeddings, node embeddings have been shown to capture certain semantics of the network structure. Combining both research directions into a joint representation learning of network structure and document content seems a promising direction to increase the quality of the learned representations. However, research is typically focused on either word or network embeddings and few approaches that learn a joint representation have been proposed. We present an overview of that field, starting at word representations, moving over document and network node representations to joint representations. We make the connections between the different models explicit and introduce a novel model for learning a joint representation. We present different methods for the novel model and compare the presented approaches in an evaluation. This paper explains how the different models recently proposed in the literature relate to each other and compares their performance.
%@ 978-3-319-66808-6
@inproceedings{10.1007/978-3-319-66808-6_16,
abstract = {Inspired by the advancements of representation learning for natural language processing, learning continuous feature representations of nodes in networks has recently gained attention. Similar to word embeddings, node embeddings have been shown to capture certain semantics of the network structure. Combining both research directions into a joint representation learning of network structure and document content seems a promising direction to increase the quality of the learned representations. However, research is typically focused on either word or network embeddings and few approaches that learn a joint representation have been proposed. We present an overview of that field, starting at word representations, moving over document and network node representations to joint representations. We make the connections between the different models explicit and introduce a novel model for learning a joint representation. We present different methods for the novel model and compare the presented approaches in an evaluation. This paper explains how the different models recently proposed in the literature relate to each other and compares their performance.},
added-at = {2020-09-30T13:16:34.000+0200},
address = {Cham},
author = {Schl{\"o}tterer, J{\"o}rg and Seifert, Christin and Granitzer, Michael},
biburl = {https://www.bibsonomy.org/bibtex/279ae24d7c3349bdab7587f107576ea6c/parismic},
booktitle = {Machine Learning and Knowledge Extraction},
description = {On Joint Representation Learning of Network Structure and Document Content | SpringerLink},
editor = {Holzinger, Andreas and Kieseberg, Peter and Tjoa, A Min and Weippl, Edgar},
interhash = {c6ee4838df79db3ef9129d3eb5ff0c4b},
intrahash = {79ae24d7c3349bdab7587f107576ea6c},
isbn = {978-3-319-66808-6},
keywords = {content network structure web},
pages = {237--251},
publisher = {Springer International Publishing},
timestamp = {2020-09-30T13:16:34.000+0200},
title = {On Joint Representation Learning of Network Structure and Document Content},
year = 2017
}