Graph in Graph Neural Network.
Saved in:
| Title: | Graph in Graph Neural Network. |
|---|---|
| Authors: | Wang, Jiongshu1 (AUTHOR) jiongshuwang@gmail.com, Yang, Jing2 (AUTHOR) y.jing2016@gmail.com, Deng, Jiankang3 (AUTHOR) jiankangdeng@gmail.com, Gunes, Hatice2 (AUTHOR) Hatice.Gunes@cl.cam.ac.uk, Song, Siyang1,2 (AUTHOR) s.song@exeter.ac.uk |
| Source: | International Journal of Computer Vision. Apr2026, Vol. 134 Issue 4, p1-24. 24p. |
| Subjects: | Graph neural networks, Multigraph, Deep learning, Human activity recognition |
| Abstract: | Existing Graph Neural Networks (GNNs) are limited to process graphs each of whose vertices is represented by a vector or a single value, limited their representing capability to describe complex objects. In this paper, we propose a novel GNN (called Graph in Graph Neural (GIG) Network) which can process graph-style data (called GIG sample) whose vertices are further represented by graphs. Given a set of graphs or a data sample whose components can be represented by a set of graphs (called multi-graph data sample), our GIG network starts with a GIG sample generation (GSG) module which encodes the input as a GIG sample, where each GIG vertex includes a graph. Then, a set of GIG hidden layers are stacked, with each consisting of: (1) a GIG vertex-level updating (GVU) module that individually updates the graph in every GIG vertex based on its internal information; and (2) a global-level GIG sample updating (GGU) module that updates graphs in all GIG vertices based on their relationships, making the updated GIG vertices become global context-aware. This way, both internal cues within the graph contained in each GIG vertex and the relationships among GIG vertices could be utilized for down-stream tasks. Experimental results demonstrate that our GIG network generalizes well for not only various generic graph analysis tasks but also real-world multi-graph data analysis (e.g., human skeleton video-based action recognition), which achieved the new state-of-the-art results on 15 out of 16 evaluated datasets. Our code is publicly available at https://github.com/wangjs96/Graph-in-Graph-Neural-Network. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Computer Vision is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 192202281 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Graph in Graph Neural Network. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Wang%2C+Jiongshu%22">Wang, Jiongshu</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> jiongshuwang@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Yang%2C+Jing%22">Yang, Jing</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> y.jing2016@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Deng%2C+Jiankang%22">Deng, Jiankang</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> jiankangdeng@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Gunes%2C+Hatice%22">Gunes, Hatice</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> Hatice.Gunes@cl.cam.ac.uk</i><br /><searchLink fieldCode="AR" term="%22Song%2C+Siyang%22">Song, Siyang</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> s.song@exeter.ac.uk</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Computer+Vision%22">International Journal of Computer Vision</searchLink>. Apr2026, Vol. 134 Issue 4, p1-24. 24p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Graph+neural+networks%22">Graph neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Multigraph%22">Multigraph</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Human+activity+recognition%22">Human activity recognition</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Existing Graph Neural Networks (GNNs) are limited to process graphs each of whose vertices is represented by a vector or a single value, limited their representing capability to describe complex objects. In this paper, we propose a novel GNN (called Graph in Graph Neural (GIG) Network) which can process graph-style data (called GIG sample) whose vertices are further represented by graphs. Given a set of graphs or a data sample whose components can be represented by a set of graphs (called multi-graph data sample), our GIG network starts with a GIG sample generation (GSG) module which encodes the input as a GIG sample, where each GIG vertex includes a graph. Then, a set of GIG hidden layers are stacked, with each consisting of: (1) a GIG vertex-level updating (GVU) module that individually updates the graph in every GIG vertex based on its internal information; and (2) a global-level GIG sample updating (GGU) module that updates graphs in all GIG vertices based on their relationships, making the updated GIG vertices become global context-aware. This way, both internal cues within the graph contained in each GIG vertex and the relationships among GIG vertices could be utilized for down-stream tasks. Experimental results demonstrate that our GIG network generalizes well for not only various generic graph analysis tasks but also real-world multi-graph data analysis (e.g., human skeleton video-based action recognition), which achieved the new state-of-the-art results on 15 out of 16 evaluated datasets. Our code is publicly available at https://github.com/wangjs96/Graph-in-Graph-Neural-Network. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of International Journal of Computer Vision is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=192202281 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s11263-026-02731-4 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 24 StartPage: 1 Subjects: – SubjectFull: Graph neural networks Type: general – SubjectFull: Multigraph Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Human activity recognition Type: general Titles: – TitleFull: Graph in Graph Neural Network. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Wang, Jiongshu – PersonEntity: Name: NameFull: Yang, Jing – PersonEntity: Name: NameFull: Deng, Jiankang – PersonEntity: Name: NameFull: Gunes, Hatice – PersonEntity: Name: NameFull: Song, Siyang IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 04 Text: Apr2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 09205691 Numbering: – Type: volume Value: 134 – Type: issue Value: 4 Titles: – TitleFull: International Journal of Computer Vision Type: main |
| ResultId | 1 |
