Identifying Informative Nodes in Attributed Spatial Sensor Networks Using Attention for Symbolic Abstraction in a GNN-based Modeling Approach

Modeling complex data, e.g. time series as well as network-based data, is a prominent area of research. In this paper, we focus on a combination of both, analyzing network-based spatial sensor data which is attributed with high frequency time series information. We apply a symbolic representation an...

Full description

Saved in:
Bibliographic Details
Main Authors: Leonid Schwenke, Stefan Bloemheuvel, Martin Atzmueller
Format: Article
Language:English
Published: LibraryPress@UF 2023-05-01
Series:Proceedings of the International Florida Artificial Intelligence Research Society Conference
Subjects:
Online Access:https://journals.flvc.org/FLAIRS/article/view/133109
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849762904743608320
author Leonid Schwenke
Stefan Bloemheuvel
Martin Atzmueller
author_facet Leonid Schwenke
Stefan Bloemheuvel
Martin Atzmueller
author_sort Leonid Schwenke
collection DOAJ
description Modeling complex data, e.g. time series as well as network-based data, is a prominent area of research. In this paper, we focus on a combination of both, analyzing network-based spatial sensor data which is attributed with high frequency time series information. We apply a symbolic representation and an attention-based local abstraction approach, to enhance interpretability on the respective complex high frequency time series data. For this, we aim at identifying informative measurements captured by the respective nodes of the sensor network. To do so, we demonstrate the efficacy of the Symbolic Fourier Approximation (SFA) and the attention-based symbolic abstraction method to localize relevant node sensor-information, by using a transformer architecture as an encoder for a graph neural network. In our experiments, we compare two seismological datasets to their previous state-of-the-art model, demonstrating the advantages and benefits of our presented approach.
format Article
id doaj-art-0bc91d6f67ba467fadff911d8227b3ff
institution DOAJ
issn 2334-0754
2334-0762
language English
publishDate 2023-05-01
publisher LibraryPress@UF
record_format Article
series Proceedings of the International Florida Artificial Intelligence Research Society Conference
spelling doaj-art-0bc91d6f67ba467fadff911d8227b3ff2025-08-20T03:05:35ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622023-05-013610.32473/flairs.36.13310969415Identifying Informative Nodes in Attributed Spatial Sensor Networks Using Attention for Symbolic Abstraction in a GNN-based Modeling ApproachLeonid Schwenke0https://orcid.org/0000-0002-2337-3905Stefan Bloemheuvel1Martin Atzmueller2https://orcid.org/0000-0002-2480-6901Osnabrück UniversityJheronimus Academy of Data ScienceOsnabr¨uck University & DFKIModeling complex data, e.g. time series as well as network-based data, is a prominent area of research. In this paper, we focus on a combination of both, analyzing network-based spatial sensor data which is attributed with high frequency time series information. We apply a symbolic representation and an attention-based local abstraction approach, to enhance interpretability on the respective complex high frequency time series data. For this, we aim at identifying informative measurements captured by the respective nodes of the sensor network. To do so, we demonstrate the efficacy of the Symbolic Fourier Approximation (SFA) and the attention-based symbolic abstraction method to localize relevant node sensor-information, by using a transformer architecture as an encoder for a graph neural network. In our experiments, we compare two seismological datasets to their previous state-of-the-art model, demonstrating the advantages and benefits of our presented approach.https://journals.flvc.org/FLAIRS/article/view/133109symbolic time series analysisgraph neural networktransformerattentioninterpretabilitylocal data reductionspatial dataseismic network
spellingShingle Leonid Schwenke
Stefan Bloemheuvel
Martin Atzmueller
Identifying Informative Nodes in Attributed Spatial Sensor Networks Using Attention for Symbolic Abstraction in a GNN-based Modeling Approach
Proceedings of the International Florida Artificial Intelligence Research Society Conference
symbolic time series analysis
graph neural network
transformer
attention
interpretability
local data reduction
spatial data
seismic network
title Identifying Informative Nodes in Attributed Spatial Sensor Networks Using Attention for Symbolic Abstraction in a GNN-based Modeling Approach
title_full Identifying Informative Nodes in Attributed Spatial Sensor Networks Using Attention for Symbolic Abstraction in a GNN-based Modeling Approach
title_fullStr Identifying Informative Nodes in Attributed Spatial Sensor Networks Using Attention for Symbolic Abstraction in a GNN-based Modeling Approach
title_full_unstemmed Identifying Informative Nodes in Attributed Spatial Sensor Networks Using Attention for Symbolic Abstraction in a GNN-based Modeling Approach
title_short Identifying Informative Nodes in Attributed Spatial Sensor Networks Using Attention for Symbolic Abstraction in a GNN-based Modeling Approach
title_sort identifying informative nodes in attributed spatial sensor networks using attention for symbolic abstraction in a gnn based modeling approach
topic symbolic time series analysis
graph neural network
transformer
attention
interpretability
local data reduction
spatial data
seismic network
url https://journals.flvc.org/FLAIRS/article/view/133109
work_keys_str_mv AT leonidschwenke identifyinginformativenodesinattributedspatialsensornetworksusingattentionforsymbolicabstractioninagnnbasedmodelingapproach
AT stefanbloemheuvel identifyinginformativenodesinattributedspatialsensornetworksusingattentionforsymbolicabstractioninagnnbasedmodelingapproach
AT martinatzmueller identifyinginformativenodesinattributedspatialsensornetworksusingattentionforsymbolicabstractioninagnnbasedmodelingapproach