Scalable Variational Gaussian Processes for Crowdsourcing: Glitch Detection in LIGO. Morales-Alvarez, P., Ruiz, P., Coughlin, S., Molina, R., & Katsaggelos, A. K. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(3):1534–1551, mar, 2022.
Scalable Variational Gaussian Processes for Crowdsourcing: Glitch Detection in LIGO [link]Paper  doi  abstract   bibtex   
In the last years, crowdsourcing is transforming the way classification training sets are obtained. Instead of relying on a single expert annotator, crowdsourcing shares the labelling effort among a large number of collaborators. For instance, this is being applied in the laureate laser interferometer gravitational waves observatory (LIGO), in order to detect glitches which might hinder the identification of true gravitational-waves. The crowdsourcing scenario poses new challenging difficulties, as it has to deal with different opinions from a heterogeneous group of annotators with unknown degrees of expertise. Probabilistic methods, such as Gaussian processes (GP), have proven successful in modeling this setting. However, GPs do not scale up well to large data sets, which hampers their broad adoption in real-world problems (in particular LIGO). This has led to the very recent introduction of deep learning based crowdsourcing methods, which have become the state-of-the-art for this type of problems. However, the accurate uncertainty quantification provided by GPs has been partially sacrificed. This is an important aspect for astrophysicists in LIGO, since a glitch detection system should provide very accurate probability distributions of its predictions. In this work, we first leverage a standard sparse GP approximation (SVGP) to develop a GP-based crowdsourcing method that factorizes into mini-batches. This makes it able to cope with previously-prohibitive data sets. This first approach, which we refer to as scalable variational Gaussian processes for crowdsourcing (SVGPCR), brings back GP-based methods to a state-of-the-art level, and excels at uncertainty quantification. SVGPCR is shown to outperform deep learning based methods and previous probabilistic ones when applied to the LIGO data. Its behavior and main properties are carefully analyzed in a controlled experiment based on the MNIST data set. Moreover, recent GP inference techniques are also adapted to crowdsourcing and evaluated experimentally.
@article{Pablo2020,
abstract = {In the last years, crowdsourcing is transforming the way classification training sets are obtained. Instead of relying on a single expert annotator, crowdsourcing shares the labelling effort among a large number of collaborators. For instance, this is being applied in the laureate laser interferometer gravitational waves observatory (LIGO), in order to detect glitches which might hinder the identification of true gravitational-waves. The crowdsourcing scenario poses new challenging difficulties, as it has to deal with different opinions from a heterogeneous group of annotators with unknown degrees of expertise. Probabilistic methods, such as Gaussian processes (GP), have proven successful in modeling this setting. However, GPs do not scale up well to large data sets, which hampers their broad adoption in real-world problems (in particular LIGO). This has led to the very recent introduction of deep learning based crowdsourcing methods, which have become the state-of-the-art for this type of problems. However, the accurate uncertainty quantification provided by GPs has been partially sacrificed. This is an important aspect for astrophysicists in LIGO, since a glitch detection system should provide very accurate probability distributions of its predictions. In this work, we first leverage a standard sparse GP approximation (SVGP) to develop a GP-based crowdsourcing method that factorizes into mini-batches. This makes it able to cope with previously-prohibitive data sets. This first approach, which we refer to as scalable variational Gaussian processes for crowdsourcing (SVGPCR), brings back GP-based methods to a state-of-the-art level, and excels at uncertainty quantification. SVGPCR is shown to outperform deep learning based methods and previous probabilistic ones when applied to the LIGO data. Its behavior and main properties are carefully analyzed in a controlled experiment based on the MNIST data set. Moreover, recent GP inference techniques are also adapted to crowdsourcing and evaluated experimentally.},
archivePrefix = {arXiv},
arxivId = {1911.01915},
author = {Morales-Alvarez, Pablo and Ruiz, Pablo and Coughlin, Scott and Molina, Rafael and Katsaggelos, Aggelos K.},
doi = {10.1109/TPAMI.2020.3025390},
eprint = {1911.01915},
issn = {0162-8828},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
keywords = {Crowdsourcing,citizen science,deep learning,laser interferometer gravitational waves observato,scalability,sparse Gaussian processes,uncertainty quantification},
month = {mar},
number = {3},
pages = {1534--1551},
pmid = {32956038},
title = {{Scalable Variational Gaussian Processes for Crowdsourcing: Glitch Detection in LIGO}},
url = {https://ieeexplore.ieee.org/document/9201029/},
volume = {44},
year = {2022}
}
Downloads: 0
About
Documentation
Keywords
Search
Users
Terms and Conditions of Use
Privacy Policy
Sitemap
© BibBase.org 2021