CommGNAS: Unsupervised Graph Neural Architecture Search for Community Detection
Article
Gao, Jianliang, Chen, Jiamin, Oloulade, Babatounde Moctard, Al-Sabri, Raeed, Lyu, Tengfei, Zhang, Ji and Li, Zhao. 2024. "CommGNAS: Unsupervised Graph Neural Architecture Search for Community Detection." IEEE Transactions on Emerging Topics in Computing. 12 (2), pp. 444-454. https://doi.org/10.1109/TETC.2023.3270181
| Article Title | CommGNAS: Unsupervised Graph Neural Architecture Search for Community Detection |
|---|---|
| ERA Journal ID | 210576 |
| Article Category | Article |
| Authors | Gao, Jianliang, Chen, Jiamin, Oloulade, Babatounde Moctard, Al-Sabri, Raeed, Lyu, Tengfei, Zhang, Ji and Li, Zhao |
| Journal Title | IEEE Transactions on Emerging Topics in Computing |
| Journal Citation | 12 (2), pp. 444-454 |
| Number of Pages | 11 |
| Year | 2024 |
| Publisher | IEEE (Institute of Electrical and Electronics Engineers) |
| Place of Publication | United States |
| ISSN | 2168-6750 |
| Digital Object Identifier (DOI) | https://doi.org/10.1109/TETC.2023.3270181 |
| Web Address (URL) | https://ieeexplore.ieee.org/document/10112632 |
| Abstract | Graph neural architecture search (GNAS) has been successful in many supervised learning tasks, such as node classification, graph classification, and link prediction. GNAS uses a search algorithm to sample graph neural network (GNN) architectures from the search space and evaluates sampled GNN architectures based on estimation strategies to generate feedback for the search algorithm. In traditional GNAS, the typical estimation strategy requires using labeled graph data to generate feedback, which plays a fundamental and vital role in the search algorithm to sample a better GNN architecture during the search process. However, a large portion of real-world graph data is unlabeled. The estimation strategy in traditional GNAS cannot use unlabeled graph data to generate feedback for the search algorithm, so the traditional supervised GNAS fails to solve unsupervised problems, such as community detection tasks. To solve this challenge, this paper proposed CommGNAS, an effective node representation learning method with unsupervised graph neural architecture search for community detection. In CommGNAS, we design an unsupervised evaluation strategy with self-supervised and self-representation learning. It represents the first research work in literature to solve the problems of unsupervised graph neural architecture search for community detection. The experimental results show that CommGNAS can obtain the best performance in community detection tasks on real-world graphs against the state-of-the-art baseline methods. |
| Keywords | Community detection; selfrepresentation learning; unsupervised graph neural architecture search; self-supervised learning; graph neural network |
| Contains Sensitive Content | Does not contain sensitive content |
| ANZSRC Field of Research 2020 | 460599. Data management and data science not elsewhere classified |
| Public Notes | The accessible file is the accepted version of the paper. Please refer to the URL for the published version. |
| Byline Affiliations | Central South University, China |
| University of Southern Queensland | |
| Zhejiang University, China |
Permalink -
https://research.usq.edu.au/item/z25w5/commgnas-unsupervised-graph-neural-architecture-search-for-community-detection
Download files
Accepted Version
| CommGNAS_Unsupervised_Graph_Neural_Architecture_Search_for_Community_Detection.pdf | ||
| File access level: Anyone | ||
53
total views51
total downloads0
views this month0
downloads this month