IFH: a Diffusion Framework for Flexible Design of Graph Generative Models
| Title: | IFH: a Diffusion Framework for Flexible Design of Graph Generative Models |
|---|---|
| Authors: | Cognolato, Samuel, Sperduti, Alessandro, Serafini, Luciano |
| Publication Year: | 2024 |
| Collection: | Computer Science Statistics |
| Subject Terms: | Computer Science - Machine Learning, Statistics - Machine Learning |
| More Details: | Graph generative models can be classified into two prominent families: one-shot models, which generate a graph in one go, and sequential models, which generate a graph by successive additions of nodes and edges. Ideally, between these two extreme models lies a continuous range of models that adopt different levels of sequentiality. This paper proposes a graph generative model, called Insert-Fill-Halt (IFH), that supports the specification of a sequentiality degree. IFH is based upon the theory of Denoising Diffusion Probabilistic Models (DDPM), designing a node removal process that gradually destroys a graph. An insertion process learns to reverse this removal process by inserting arcs and nodes according to the specified sequentiality degree. We evaluate the performance of IFH in terms of quality, run time, and memory, depending on different sequentiality degrees. We also show that using DiGress, a diffusion-based one-shot model, as a generative step in IFH leads to improvement to the model itself, and is competitive with the current state-of-the-art. Comment: Accepted at the 27th European Conference on Artificial Intelligence (ECAI 24) |
| Document Type: | Working Paper |
| Access URL: | http://arxiv.org/abs/2408.13194 |
| Accession Number: | edsarx.2408.13194 |
| Database: | arXiv |
| FullText | Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2408.13194 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20240823&spage=&pages=&title=IFH: a Diffusion Framework for Flexible Design of Graph Generative Models&atitle=IFH%3A%20a%20Diffusion%20Framework%20for%20Flexible%20Design%20of%20Graph%20Generative%20Models&aulast=Cognolato%2C%20Samuel&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries |
|---|---|
| Header | DbId: edsarx DbLabel: arXiv An: edsarx.2408.13194 RelevancyScore: 1112 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1112.24499511719 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: IFH: a Diffusion Framework for Flexible Design of Graph Generative Models – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Cognolato%2C+Samuel%22">Cognolato, Samuel</searchLink><br /><searchLink fieldCode="AR" term="%22Sperduti%2C+Alessandro%22">Sperduti, Alessandro</searchLink><br /><searchLink fieldCode="AR" term="%22Serafini%2C+Luciano%22">Serafini, Luciano</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2024 – Name: Subset Label: Collection Group: HoldingsInfo Data: Computer Science<br />Statistics – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Machine+Learning%22">Computer Science - Machine Learning</searchLink><br /><searchLink fieldCode="DE" term="%22Statistics+-+Machine+Learning%22">Statistics - Machine Learning</searchLink> – Name: Abstract Label: Description Group: Ab Data: Graph generative models can be classified into two prominent families: one-shot models, which generate a graph in one go, and sequential models, which generate a graph by successive additions of nodes and edges. Ideally, between these two extreme models lies a continuous range of models that adopt different levels of sequentiality. This paper proposes a graph generative model, called Insert-Fill-Halt (IFH), that supports the specification of a sequentiality degree. IFH is based upon the theory of Denoising Diffusion Probabilistic Models (DDPM), designing a node removal process that gradually destroys a graph. An insertion process learns to reverse this removal process by inserting arcs and nodes according to the specified sequentiality degree. We evaluate the performance of IFH in terms of quality, run time, and memory, depending on different sequentiality degrees. We also show that using DiGress, a diffusion-based one-shot model, as a generative step in IFH leads to improvement to the model itself, and is competitive with the current state-of-the-art.<br />Comment: Accepted at the 27th European Conference on Artificial Intelligence (ECAI 24) – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2408.13194" linkWindow="_blank">http://arxiv.org/abs/2408.13194</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2408.13194 |
| PLink | https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2408.13194 |
| RecordInfo | BibRecord: BibEntity: Subjects: – SubjectFull: Computer Science - Machine Learning Type: general – SubjectFull: Statistics - Machine Learning Type: general Titles: – TitleFull: IFH: a Diffusion Framework for Flexible Design of Graph Generative Models Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Cognolato, Samuel – PersonEntity: Name: NameFull: Sperduti, Alessandro – PersonEntity: Name: NameFull: Serafini, Luciano IsPartOfRelationships: – BibEntity: Dates: – D: 23 M: 08 Type: published Y: 2024 |
| ResultId | 1 |