Augmenting Structure with Text for Improved Graph Learning
dc.contributor.author | Safavi, Tara | |
dc.date.accessioned | 2022-09-06T16:17:56Z | |
dc.date.available | 2022-09-06T16:17:56Z | |
dc.date.issued | 2022 | |
dc.date.submitted | 2022 | |
dc.identifier.uri | https://hdl.handle.net/2027.42/174515 | |
dc.description.abstract | Many important problems in machine learning and data mining, such as knowledge base reasoning, personalized entity recommendation, and scientific hypothesis generation, may be framed as learning and inference over a graph data structure. Such problems represent exciting opportunities for advancing graph learning, but also entail significant challenges. Because graphs are typically sparse and defined by a schema, they often do not fully capture the underlying complex relationships in the data. Models that combine graphs with rich auxiliary textual modalities have higher potential for expressiveness, but jointly processing such disparate modalities--that is, sparse structured relations and dense unstructured text--is not straightforward. In this thesis, we consider the important problem of improving graph learning by combining structure and text. The first part of the thesis considers relational knowledge representation and reasoning tasks, demonstrating the great potential of pretrained contextual language models to add renewed depth and richness to graph-structured knowledge bases. The second part of the thesis goes beyond knowledge bases, toward improving graph learning tasks that arise in information retrieval and recommender systems by jointly modeling document interactions and content. Our proposed methodologies consistently improve accuracy over both single-modality and cross-modality baselines, suggesting that, with appropriately chosen inductive biases and careful model design, we can exploit the unique complementary aspects of structure and text to great effect. | |
dc.language.iso | en_US | |
dc.subject | text-augmented graph learning | |
dc.subject | knowledge representation and reasoning | |
dc.subject | interaction and content mining | |
dc.subject | machine learning | |
dc.title | Augmenting Structure with Text for Improved Graph Learning | |
dc.type | Thesis | |
dc.description.thesisdegreename | PhD | en_US |
dc.description.thesisdegreediscipline | Computer Science & Engineering | |
dc.description.thesisdegreegrantor | University of Michigan, Horace H. Rackham School of Graduate Studies | |
dc.contributor.committeemember | Koutra, Danai | |
dc.contributor.committeemember | Collins-Thompson, Kevyn | |
dc.contributor.committeemember | Bennett, Paul | |
dc.contributor.committeemember | Wang, Lu | |
dc.subject.hlbsecondlevel | Computer Science | |
dc.subject.hlbtoplevel | Engineering | |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/174515/1/tsafavi_1.pdf | |
dc.identifier.doi | https://dx.doi.org/10.7302/6246 | |
dc.identifier.orcid | 0000-0002-3553-4331 | |
dc.identifier.name-orcid | Safavi, Tara; 0000-0002-3553-4331 | en_US |
dc.working.doi | 10.7302/6246 | en |
dc.owningcollname | Dissertations and Theses (Ph.D. and Master's) |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.