Report
Efficient Graph Condensation via Gaussian Process
| العنوان: | Efficient Graph Condensation via Gaussian Process |
|---|---|
| المؤلفون: | Wang, Lin, Li, Qing |
| سنة النشر: | 2025 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Machine Learning |
| الوصف: | Graph condensation reduces the size of large graphs while preserving performance, addressing the scalability challenges of Graph Neural Networks caused by computational inefficiencies on large datasets. Existing methods often rely on bi-level optimization, requiring extensive GNN training and limiting their scalability. To address these issues, this paper proposes Graph Condensation via Gaussian Process (GCGP), a novel and computationally efficient approach to graph condensation. GCGP utilizes a Gaussian Process (GP), with the condensed graph serving as observations, to estimate the posterior distribution of predictions. This approach eliminates the need for the iterative and resource-intensive training typically required by GNNs. To enhance the capability of the GCGP in capturing dependencies between function values, we derive a specialized covariance function that incorporates structural information. This covariance function broadens the receptive field of input nodes by local neighborhood aggregation, thereby facilitating the representation of intricate dependencies within the nodes. To address the challenge of optimizing binary structural information in condensed graphs, Concrete random variables are utilized to approximate the binary adjacency matrix in a continuous counterpart. This relaxation process allows the adjacency matrix to be represented in a differentiable form, enabling the application of gradient-based optimization techniques to discrete graph structures. Experimental results show that the proposed GCGP method efficiently condenses large-scale graph data while preserving predictive performance, addressing the scalability and efficiency challenges. The implementation of our method is publicly available at https://github.com/WANGLin0126/GCGP. |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2501.02565 |
| رقم الانضمام: | edsarx.2501.02565 |
| قاعدة البيانات: | arXiv |
| ResultId |
1 |
|---|---|
| Header |
edsarx arXiv edsarx.2501.02565 1147 3 Report report 1146.55029296875 |
| PLink |
https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2501.02565&custid=s6537998&authtype=sso |
| FullText |
Array
(
[Availability] => 0
)
Array ( [0] => Array ( [Url] => http://arxiv.org/abs/2501.02565 [Name] => EDS - Arxiv [Category] => fullText [Text] => View record in Arxiv [MouseOverText] => View record in Arxiv ) ) |
| Items |
Array
(
[Name] => Title
[Label] => Title
[Group] => Ti
[Data] => Efficient Graph Condensation via Gaussian Process
)
Array ( [Name] => Author [Label] => Authors [Group] => Au [Data] => <searchLink fieldCode="AR" term="%22Wang%2C+Lin%22">Wang, Lin</searchLink><br /><searchLink fieldCode="AR" term="%22Li%2C+Qing%22">Li, Qing</searchLink> ) Array ( [Name] => DatePubCY [Label] => Publication Year [Group] => Date [Data] => 2025 ) Array ( [Name] => Subset [Label] => Collection [Group] => HoldingsInfo [Data] => Computer Science ) Array ( [Name] => Subject [Label] => Subject Terms [Group] => Su [Data] => <searchLink fieldCode="DE" term="%22Computer+Science+-+Machine+Learning%22">Computer Science - Machine Learning</searchLink> ) Array ( [Name] => Abstract [Label] => Description [Group] => Ab [Data] => Graph condensation reduces the size of large graphs while preserving performance, addressing the scalability challenges of Graph Neural Networks caused by computational inefficiencies on large datasets. Existing methods often rely on bi-level optimization, requiring extensive GNN training and limiting their scalability. To address these issues, this paper proposes Graph Condensation via Gaussian Process (GCGP), a novel and computationally efficient approach to graph condensation. GCGP utilizes a Gaussian Process (GP), with the condensed graph serving as observations, to estimate the posterior distribution of predictions. This approach eliminates the need for the iterative and resource-intensive training typically required by GNNs. To enhance the capability of the GCGP in capturing dependencies between function values, we derive a specialized covariance function that incorporates structural information. This covariance function broadens the receptive field of input nodes by local neighborhood aggregation, thereby facilitating the representation of intricate dependencies within the nodes. To address the challenge of optimizing binary structural information in condensed graphs, Concrete random variables are utilized to approximate the binary adjacency matrix in a continuous counterpart. This relaxation process allows the adjacency matrix to be represented in a differentiable form, enabling the application of gradient-based optimization techniques to discrete graph structures. Experimental results show that the proposed GCGP method efficiently condenses large-scale graph data while preserving predictive performance, addressing the scalability and efficiency challenges. The implementation of our method is publicly available at https://github.com/WANGLin0126/GCGP. ) Array ( [Name] => TypeDocument [Label] => Document Type [Group] => TypDoc [Data] => Working Paper ) Array ( [Name] => URL [Label] => Access URL [Group] => URL [Data] => <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2501.02565" linkWindow="_blank">http://arxiv.org/abs/2501.02565</link> ) Array ( [Name] => AN [Label] => Accession Number [Group] => ID [Data] => edsarx.2501.02565 ) |
| RecordInfo |
Array
(
[BibEntity] => Array
(
[Subjects] => Array
(
[0] => Array
(
[SubjectFull] => Computer Science - Machine Learning
[Type] => general
)
)
[Titles] => Array
(
[0] => Array
(
[TitleFull] => Efficient Graph Condensation via Gaussian Process
[Type] => main
)
)
)
[BibRelationships] => Array
(
[HasContributorRelationships] => Array
(
[0] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Wang, Lin
)
)
)
[1] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Li, Qing
)
)
)
)
[IsPartOfRelationships] => Array
(
[0] => Array
(
[BibEntity] => Array
(
[Dates] => Array
(
[0] => Array
(
[D] => 05
[M] => 01
[Type] => published
[Y] => 2025
)
)
)
)
)
)
)
|
| IllustrationInfo |