VTechWorks staff will be away for the Thanksgiving holiday beginning at noon on Wednesday, November 27, through Friday, November 29. We will resume normal operations on Monday, December 2. Thank you for your patience.
 

Deep Representation Learning on Labeled Graphs

Simple item page
dc.contributor.authorFan, Shuangfeien
dc.contributor.committeechairHuang, Berten
dc.contributor.committeememberNeville, Jenniferen
dc.contributor.committeememberAbbott, A. Lynnen
dc.contributor.committeememberRamakrishnan, Narenen
dc.contributor.committeememberReddy, Chandan K.en
dc.contributor.departmentComputer Scienceen
dc.date.accessioned2020-01-28T09:01:37Zen
dc.date.available2020-01-28T09:01:37Zen
dc.date.issued2020-01-27en
dc.description.abstractWe introduce recurrent collective classification (RCC), a variant of ICA analogous to recurrent neural network prediction. RCC accommodates any differentiable local classifier and relational feature functions. We provide gradient-based strategies for optimizing over model parameters to more directly minimize the loss function. In our experiments, this direct loss minimization translates to improved accuracy and robustness on real network data. We demonstrate the robustness of RCC in settings where local classification is very noisy, settings that are particularly challenging for ICA. As a new way to train generative models, generative adversarial networks (GANs) have achieved considerable success in image generation, and this framework has also recently been applied to data with graph structures. We identify the drawbacks of existing deep frameworks for generating graphs, and we propose labeled-graph generative adversarial networks (LGGAN) to train deep generative models for graph-structured data with node labels. We test the approach on various types of graph datasets, such as collections of citation networks and protein graphs. Experiment results show that our model can generate diverse labeled graphs that match the structural characteristics of the training data and outperforms all baselines in terms of quality, generality, and scalability. To further evaluate the quality of the generated graphs, we apply it to a downstream task for graph classification, and the results show that LGGAN can better capture the important aspects of the graph structure.en
dc.description.abstractgeneralGraphs are one of the most important and powerful data structures for conveying the complex and correlated information among data points. In this research, we aim to provide more robust and accurate models for some graph specific tasks, such as collective classification and graph generation, by designing deep learning models to learn better task-specific representations for graphs. First, we studied the collective classification problem in graphs and proposed recurrent collective classification, a variant of the iterative classification algorithm that is more robust to situations where predictions are noisy or inaccurate. Then we studied the problem of graph generation using deep generative models. We first proposed a deep generative model using the GAN framework that generates labeled graphs. Then in order to support more applications and also get more control over the generated graphs, we extended the problem of graph generation to conditional graph generation which can then be applied to various applications for modeling graph evolution and transformation.en
dc.description.degreeDoctor of Philosophyen
dc.format.mediumETDen
dc.identifier.othervt_gsexam:23781en
dc.identifier.urihttp://hdl.handle.net/10919/96596en
dc.language.isoenen
dc.publisherVirginia Techen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectMachine learningen
dc.titleDeep Representation Learning on Labeled Graphsen
dc.typeDissertationen
thesis.degree.disciplineComputer Science and Applicationsen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.leveldoctoralen
thesis.degree.nameDoctor of Philosophyen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Fan_S_D_2020.pdf
Size:
7.06 MB
Format:
Adobe Portable Document Format
Download

Collections

Doctoral Dissertations