Publication:
Problems in Graph-Structured Modeling and Learning

Simple item page
dc.contributor.advisorDon Towsley
dc.contributor.advisorBenjamin Marlin
dc.contributor.advisorGerome Miklau
dc.contributor.advisorWeibo Gong
dc.contributor.authorAtwood, James
dc.contributor.departmentUniversity of Massachusetts Amherst
dc.date2024-03-27T19:39:00.000
dc.date.accessioned2024-04-26T16:18:58Z
dc.date.available2024-04-26T16:18:58Z
dc.date.submittedMay
dc.date.submitted2017
dc.description.abstractThis thesis investigates three problems in graph-structured modeling and learning. We first present a method for efficiently generating large instances from nonlinear preferential attachment models of network structure. This is followed by a description of diffusion-convolutional neural networks, a new model for graph-structured data which is able to outperform probabilistic relational models and kernel-on-graph methods at node classification tasks. We conclude with an optimal privacy-protection method for users of online services that remains effective when users have poor knowledge of an adversary's behavior.
dc.description.degreeDoctor of Philosophy (PhD)
dc.description.departmentComputer Science
dc.identifier.doihttps://doi.org/10.7275/10010449.0
dc.identifier.orcidN/A
dc.identifier.urihttps://hdl.handle.net/20.500.14394/20196
dc.relation.urlhttps://scholarworks.umass.edu/cgi/viewcontent.cgi?article=2039&context=dissertations_2&unstamped=1
dc.source.statuspublished
dc.subjectnetwork science
dc.subjectmachine learning
dc.subjectneural network
dc.subjectpreferential attachment
dc.subjectprivacy
dc.subjectArtificial Intelligence and Robotics
dc.subjectInformation Security
dc.subjectPhysics
dc.subjectTheory and Algorithms
dc.titleProblems in Graph-Structured Modeling and Learning
dc.typeopenaccess
dc.typearticle
dc.typedissertation
digcom.contributor.authorisAuthorOfPublication|email:jatwood@cs.umass.edu|institution:University of Massachusetts Amherst|Atwood, James
digcom.identifierdissertations_2/929
digcom.identifier.contextkey10010449
digcom.identifier.submissionpathdissertations_2/929
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Thesis_umass_revisions.pdf
Size:
3.33 MB
Format:
Adobe Portable Document Format
Name: Thesis_umass_revisions.pdf
Size: 3.33 MB
Kind: Adobe PDF
Collections
Dissertations