Dissertation/ Thesis
Neural Architectures for Searching Subgraph Structures
| Title: | Neural Architectures for Searching Subgraph Structures |
|---|---|
| Authors: | Radin Hamidi Rad |
| Publication Year: | 2026 |
| Subject Terms: | Information retrieval, Computer engineering, n.e.c, Graph searching, Graph theory -- Data processing, Neural networks (Computer science), Subgraph structures, Algorithms, Mathematical models |
| Description: | With the development of new neural network architectures for graph representation learning in recent years, the use of graphs to store, represent and process data has become increasingly more important. This thesis focuses on both structural and semantic aspects of graphs in order to design and develop neural representation learning models that are capable of performing effective and efficient search on graphs in order to identify and retrieve relevant subgraph structures. Graph search is an NP-hard problem, with existing methods struggling to balance accuracy and efficiency. This work aims to design robust neural representations that address these challenges. The first contribution examines team formation as a case study of search within complete graphs. Team formation is concerned with the identification of a group of experts who have a high likelihood of effectively collaborating with each other in order to satisfy a collection of input skills. This thesis proposes a variational Bayesian neural network architecture that learns representations for teams whose members have collaborated with each other in the past. The learnt representations allow our proposed approach to mine teams that have a past collaborative history and collectively cover the requested desirable set of skills. Through our experiments on DBLP and Dota2 datasets, we demonstrate that our approach shows stronger performance compared to a range of strong team formation techniques from both quantitative and quality perspectives. Furthermore, we redefine team discovery as a task of learning subgraph representations from heterogeneous collaboration networks. Our method captures both local (node interactions within teams) and global (subgraph interactions between teams) characteristics, enabling seamless mapping between homogeneous and heterogeneous subgraphs to effectively discover teams. Extensive experiments on two real-world datasets confirm the effectiveness of the approach. In the context of incomplete graphs, we introduce a novel graph neural ... |
| Document Type: | thesis |
| Language: | unknown |
| Relation: | https://figshare.com/articles/thesis/Neural_Architectures_for_Searching_Subgraph_Structures/31175350 |
| DOI: | 10.32920/31175350.v2 |
| Availability: | https://doi.org/10.32920/31175350.v2 https://figshare.com/articles/thesis/Neural_Architectures_for_Searching_Subgraph_Structures/31175350 |
| Rights: | In Copyright |
| Accession Number: | edsbas.1FAFA0FA |
| Database: | BASE |
| FullText | Text: Availability: 0 CustomLinks: – Url: https://doi.org/10.32920/31175350.v2# Name: EDS - BASE (ns324271) Category: fullText Text: View record from BASE |
|---|---|
| Header | DbId: edsbas DbLabel: BASE An: edsbas.1FAFA0FA RelevancyScore: 877 AccessLevel: 3 PubType: Dissertation/ Thesis PubTypeId: dissertation PreciseRelevancyScore: 876.808898925781 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Neural Architectures for Searching Subgraph Structures – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Radin+Hamidi+Rad%22">Radin Hamidi Rad</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2026 – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Information+retrieval%22">Information retrieval</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+engineering%22">Computer engineering</searchLink><br /><searchLink fieldCode="DE" term="%22n%2Ee%2Ec%22">n.e.c</searchLink><br /><searchLink fieldCode="DE" term="%22Graph+searching%22">Graph searching</searchLink><br /><searchLink fieldCode="DE" term="%22Graph+theory+--+Data+processing%22">Graph theory -- Data processing</searchLink><br /><searchLink fieldCode="DE" term="%22Neural+networks+%28Computer+science%29%22">Neural networks (Computer science)</searchLink><br /><searchLink fieldCode="DE" term="%22Subgraph+structures%22">Subgraph structures</searchLink><br /><searchLink fieldCode="DE" term="%22Algorithms%22">Algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+models%22">Mathematical models</searchLink> – Name: Abstract Label: Description Group: Ab Data: With the development of new neural network architectures for graph representation learning in recent years, the use of graphs to store, represent and process data has become increasingly more important. This thesis focuses on both structural and semantic aspects of graphs in order to design and develop neural representation learning models that are capable of performing effective and efficient search on graphs in order to identify and retrieve relevant subgraph structures. Graph search is an NP-hard problem, with existing methods struggling to balance accuracy and efficiency. This work aims to design robust neural representations that address these challenges. The first contribution examines team formation as a case study of search within complete graphs. Team formation is concerned with the identification of a group of experts who have a high likelihood of effectively collaborating with each other in order to satisfy a collection of input skills. This thesis proposes a variational Bayesian neural network architecture that learns representations for teams whose members have collaborated with each other in the past. The learnt representations allow our proposed approach to mine teams that have a past collaborative history and collectively cover the requested desirable set of skills. Through our experiments on DBLP and Dota2 datasets, we demonstrate that our approach shows stronger performance compared to a range of strong team formation techniques from both quantitative and quality perspectives. Furthermore, we redefine team discovery as a task of learning subgraph representations from heterogeneous collaboration networks. Our method captures both local (node interactions within teams) and global (subgraph interactions between teams) characteristics, enabling seamless mapping between homogeneous and heterogeneous subgraphs to effectively discover teams. Extensive experiments on two real-world datasets confirm the effectiveness of the approach. In the context of incomplete graphs, we introduce a novel graph neural ... – Name: TypeDocument Label: Document Type Group: TypDoc Data: thesis – Name: Language Label: Language Group: Lang Data: unknown – Name: NoteTitleSource Label: Relation Group: SrcInfo Data: https://figshare.com/articles/thesis/Neural_Architectures_for_Searching_Subgraph_Structures/31175350 – Name: DOI Label: DOI Group: ID Data: 10.32920/31175350.v2 – Name: URL Label: Availability Group: URL Data: https://doi.org/10.32920/31175350.v2<br />https://figshare.com/articles/thesis/Neural_Architectures_for_Searching_Subgraph_Structures/31175350 – Name: Copyright Label: Rights Group: Cpyrght Data: In Copyright – Name: AN Label: Accession Number Group: ID Data: edsbas.1FAFA0FA |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.1FAFA0FA |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.32920/31175350.v2 Languages: – Text: unknown Subjects: – SubjectFull: Information retrieval Type: general – SubjectFull: Computer engineering Type: general – SubjectFull: n.e.c Type: general – SubjectFull: Graph searching Type: general – SubjectFull: Graph theory -- Data processing Type: general – SubjectFull: Neural networks (Computer science) Type: general – SubjectFull: Subgraph structures Type: general – SubjectFull: Algorithms Type: general – SubjectFull: Mathematical models Type: general Titles: – TitleFull: Neural Architectures for Searching Subgraph Structures Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Radin Hamidi Rad IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 01 Type: published Y: 2026 Identifiers: – Type: issn-locals Value: edsbas |
| ResultId | 1 |