Spatio-temporal forecasting over graphs with deep learning

buir.advisorKozat, Süleyman Serdar
dc.contributor.authorCeyani, Emir
dc.date.accessioned2020-12-23T07:30:45Z
dc.date.available2020-12-23T07:30:45Z
dc.date.copyright2020-12
dc.date.issued2020-12
dc.date.submitted2020-12-22
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.descriptionCataloged from PDF version of article.en_US
dc.descriptionThesis (Master's): Bilkent University, Department of Electrical and Electronics Engineering, İhsan Doğramacı Bilkent University, 2020.en_US
dc.descriptionIncludes bibliographical references (leaves 58-72).en_US
dc.description.abstractWe study spatiotemporal forecasting of high-dimensional rectangular grid graph structured data, which exhibits both complex spatial and temporal dependencies. In most high-dimensional spatiotemporal forecasting scenarios, deep learningbased methods are widely used. However, deep learning algorithms are overconfident in their predictions, and this overconfidence causes problems in the human-in-the-loop domains such as medical diagnosis and many applications of 5 th generation wireless networks. We propose spatiotemporal extensions to variational autoencoders for regularization, robustness against out-of data distribution, and incorporating uncertainty in predictions to resolve overconfident predictions. However, variational inference methods are prone to biased posterior approximations due to using explicit exponential family densities and mean-field assumption in their posterior factorizations. To mitigate these problems, we utilize variational inference & learning with semi-implicit distributions and apply this inference scheme into convolutional long-short term memory networks(ConvLSTM) for the first time in the literature. In chapter 3, we propose variational autoencoders with convolutional long-short term memory networks, called VarConvLSTM. In chapter 4, we improve our algorithm via semi-implicit & doubly semi-implicit variational inference to model multi-modalities in the data distribution . In chapter 5, we demonstrate that proposed algorithms are applicable for spatiotemporal forecasting tasks, including space-time mobile traffic forecasting over Turkcell base station networks.en_US
dc.description.degreeM.S.en_US
dc.description.statementofresponsibilityby Emir Ceyanien_US
dc.embargo.release2021-06-08
dc.format.extentxiv, 72 leaves : illustrations (some color) ; 30 cm.en_US
dc.identifier.itemidB125768
dc.identifier.urihttp://hdl.handle.net/11693/54851
dc.language.isoEnglishen_US
dc.publisherBilkent Universityen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectDeep learningen_US
dc.subjectGenerative modelsen_US
dc.subjectApproximate bayesian inferenceen_US
dc.subjectVariational inferenceen_US
dc.subjectConvolutional neural networksen_US
dc.subjectRecurrent neural networksen_US
dc.subjectSpatiotemporal modelingen_US
dc.subjectSupervised learningen_US
dc.titleSpatio-temporal forecasting over graphs with deep learningen_US
dc.title.alternativeDerin öğrenme ile çizgelerde uzay zamansal tahminlemeen_US
dc.typeThesisen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
thesis-ceyani-emir.pdf
Size:
824.81 KB
Format:
Adobe Portable Document Format
Description:
Full printable version
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: