Identifying Informative Nodes in Attributed Spatial Sensor Networks Using Attention for Symbolic Abstraction in a GNN-based Modeling Approach
Autor(en): | Schwenke, Leonid Bloemheuvel, Stefan Atzmueller, Martin |
Herausgeber: | Franklin, M. Chun, S.A. |
Stichwörter: | Attention; Complex networks; Graph Neural Network; Graph neural networks; Interpretability; Local data; Local Data Reduction; Machine learning; Seismic Network; Seismic networks; Seismology; Sensor nodes; Spatial Data; Spatial sensors; Symbolic Time Series Analysis; Time series analysis; Transformer | Erscheinungsdatum: | 2023 | Herausgeber: | Florida OJ | Journal: | Proceedings of the International Florida Artificial Intelligence Research Society Conference, FLAIRS | Volumen: | 36 | Zusammenfassung: | 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 exper-iments, we compare two seismological datasets to their previous state-of-the-art model, demonstrating the ad-vantages and benefits of our presented approach. © 2023 by the authors. All rights reserved. |
Beschreibung: | Cited by: 0; Conference name: 36th International Florida Artificial Intelligence Research Society Conference, FLAIRS-36 2023; Conference date: 14 May 2023 through 17 May 2023; Conference code: 294329 |
ISSN: | 2334-0754 | DOI: | 10.32473/flairs.36.133109 | Externe URL: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85161460349&doi=10.32473%2fflairs.36.133109&partnerID=40&md5=3138ff399bbd3690dbbede93f593833b |
Zur Langanzeige
Seitenaufrufe
1
Letzte Woche
0
0
Letzter Monat
0
0
geprüft am 18.05.2024