Topology‐aware tensor decomposition for meta‐graph learning
Abstract Heterogeneous graphs generally refer to graphs with different types of nodes and edges. A common approach for extracting useful information from heterogeneous graphs is to use meta‐graphs, which can be seen as a special kind of directed acyclic graph with same node and edge types as the het...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-06-01
|
| Series: | CAAI Transactions on Intelligence Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cit2.12404 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850121635748642816 |
|---|---|
| author | Hansi Yang Quanming Yao |
| author_facet | Hansi Yang Quanming Yao |
| author_sort | Hansi Yang |
| collection | DOAJ |
| description | Abstract Heterogeneous graphs generally refer to graphs with different types of nodes and edges. A common approach for extracting useful information from heterogeneous graphs is to use meta‐graphs, which can be seen as a special kind of directed acyclic graph with same node and edge types as the heterogeneous graph. However, how to design proper meta‐graphs is challenging. Recently, there have been many works on learning suitable meta‐graphs from a heterogeneous graph. Existing methods generally introduce continuous weights for edges that are independent of each other, which ignores the topological structures of meta‐graphs and can be ineffective. To address this issue, the authors propose a new viewpoint from tensor on learning meta‐graphs. Such a viewpoint not only helps interpret the limitation of existing works by CANDECOMP/PARAFAC (CP) decomposition, but also inspires us to propose a topology‐aware tensor decomposition, called TENSUS, that reflects the structure of DAGs. The proposed topology‐aware tensor decomposition is easy to use and simple to implement, and it can be taken as a plug‐in part to upgrade many existing works, including node classification and recommendation on heterogeneous graphs. Experimental results on different tasks demonstrate that the proposed method can significantly improve the state‐of‐the‐arts for all these tasks. |
| format | Article |
| id | doaj-art-42cca0d72f2c4e258c482bf4f94182c7 |
| institution | OA Journals |
| issn | 2468-2322 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | CAAI Transactions on Intelligence Technology |
| spelling | doaj-art-42cca0d72f2c4e258c482bf4f94182c72025-08-20T02:35:01ZengWileyCAAI Transactions on Intelligence Technology2468-23222025-06-0110389190110.1049/cit2.12404Topology‐aware tensor decomposition for meta‐graph learningHansi Yang0Quanming Yao1Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong ChinaDepartment of Electronic Engineering Tsinghua University Beijing ChinaAbstract Heterogeneous graphs generally refer to graphs with different types of nodes and edges. A common approach for extracting useful information from heterogeneous graphs is to use meta‐graphs, which can be seen as a special kind of directed acyclic graph with same node and edge types as the heterogeneous graph. However, how to design proper meta‐graphs is challenging. Recently, there have been many works on learning suitable meta‐graphs from a heterogeneous graph. Existing methods generally introduce continuous weights for edges that are independent of each other, which ignores the topological structures of meta‐graphs and can be ineffective. To address this issue, the authors propose a new viewpoint from tensor on learning meta‐graphs. Such a viewpoint not only helps interpret the limitation of existing works by CANDECOMP/PARAFAC (CP) decomposition, but also inspires us to propose a topology‐aware tensor decomposition, called TENSUS, that reflects the structure of DAGs. The proposed topology‐aware tensor decomposition is easy to use and simple to implement, and it can be taken as a plug‐in part to upgrade many existing works, including node classification and recommendation on heterogeneous graphs. Experimental results on different tasks demonstrate that the proposed method can significantly improve the state‐of‐the‐arts for all these tasks.https://doi.org/10.1049/cit2.12404graph neural networkheterogeneous graphpolymorphic networktensor decomposition |
| spellingShingle | Hansi Yang Quanming Yao Topology‐aware tensor decomposition for meta‐graph learning CAAI Transactions on Intelligence Technology graph neural network heterogeneous graph polymorphic network tensor decomposition |
| title | Topology‐aware tensor decomposition for meta‐graph learning |
| title_full | Topology‐aware tensor decomposition for meta‐graph learning |
| title_fullStr | Topology‐aware tensor decomposition for meta‐graph learning |
| title_full_unstemmed | Topology‐aware tensor decomposition for meta‐graph learning |
| title_short | Topology‐aware tensor decomposition for meta‐graph learning |
| title_sort | topology aware tensor decomposition for meta graph learning |
| topic | graph neural network heterogeneous graph polymorphic network tensor decomposition |
| url | https://doi.org/10.1049/cit2.12404 |
| work_keys_str_mv | AT hansiyang topologyawaretensordecompositionformetagraphlearning AT quanmingyao topologyawaretensordecompositionformetagraphlearning |