Node embedding has recently shown state-of-the-
art performance in various network analysis tasks. However,
most of the existing node embedding methods do not consider
the uncertainty of the input data, which is often the case in
practice. This work offers an empirical evaluation of the typical
node embedding methods when applied on uncertain networks.
Precisely, we examine the performance of embedding vectors
obtained by these methods in a set of downstream tasks. To
this end, we employ a wide range of uncertain networks and
traditional prepossessing techniques for dealing with uncertainty.
Our findings suggest that the existing node embedding methods
perform practically well on networks with uncertainty once the
network data is appropriately prepossessed.
%0 Generic
%1 nguyen2020embedding
%A Hoang H. Nguyen,
%A Sergej Zerr,
%A Tuan-Anh Hoang,
%B 2020 IEEE International Conference on Big Data (IEEE BigData 2020), Atlanta, Georgia, USA, December 10-13, 2020
%D December 2020
%K analysis embedding myown network networks node uncertain
%T On Node Embedding of Uncertain Networks
%X Node embedding has recently shown state-of-the-
art performance in various network analysis tasks. However,
most of the existing node embedding methods do not consider
the uncertainty of the input data, which is often the case in
practice. This work offers an empirical evaluation of the typical
node embedding methods when applied on uncertain networks.
Precisely, we examine the performance of embedding vectors
obtained by these methods in a set of downstream tasks. To
this end, we employ a wide range of uncertain networks and
traditional prepossessing techniques for dealing with uncertainty.
Our findings suggest that the existing node embedding methods
perform practically well on networks with uncertainty once the
network data is appropriately prepossessed.
@conference{nguyen2020embedding,
abstract = {Node embedding has recently shown state-of-the-
art performance in various network analysis tasks. However,
most of the existing node embedding methods do not consider
the uncertainty of the input data, which is often the case in
practice. This work offers an empirical evaluation of the typical
node embedding methods when applied on uncertain networks.
Precisely, we examine the performance of embedding vectors
obtained by these methods in a set of downstream tasks. To
this end, we employ a wide range of uncertain networks and
traditional prepossessing techniques for dealing with uncertainty.
Our findings suggest that the existing node embedding methods
perform practically well on networks with uncertainty once the
network data is appropriately prepossessed.},
added-at = {2021-03-03T16:30:22.000+0100},
author = {{Hoang H. Nguyen} and {Sergej Zerr} and {Tuan-Anh Hoang}},
biburl = {https://www.bibsonomy.org/bibtex/276ac9e16899c04133da4667655727e40/erichoang},
booktitle = {2020 IEEE International Conference on Big Data (IEEE BigData 2020), Atlanta, Georgia, USA, December 10-13, 2020},
eventdate = {December 10-13, 2020},
eventtitle = {IEEE BigData 2020},
interhash = {b310ee7d239ae4acf5d32f74fb3f8f70},
intrahash = {76ac9e16899c04133da4667655727e40},
keywords = {analysis embedding myown network networks node uncertain},
timestamp = {2021-03-03T17:23:02.000+0100},
title = {On Node Embedding of Uncertain Networks},
venue = {2020 IEEE International Conference on Big Data (IEEE BigData 2020), Atlanta, Georgia, USA, December 10-13, 2020},
year = {December 2020}
}