Alternating-update-strategy based Graph Autoencoder for graph neural network
Uloženo v:
| Název: | Alternating-update-strategy based Graph Autoencoder for graph neural network |
|---|---|
| Autoři: | Lingxiao Shan, Jian Li, Guanjun Liu |
| Zdroj: | The Computer Journal. 68:830-838 |
| Informace o vydavateli: | Oxford University Press (OUP), 2025. |
| Rok vydání: | 2025 |
| Popis: | Self-supervised learning (SSL) has become a promising and popular learning paradigm for graph data, offering the advantage of capturing informative knowledge without reliance on manual labels. As a representative class of generative graph SSL models, existing graph autoencoders (GAE) excel in link prediction tasks and are steadily improving in node classification tasks. However, GAE is essentially based on the Information Maximization (InfoMax) principle, always captures much redundant information. In this paper, we propose an Alternating-update-strategy based Graph Autoencoder, including alternating update module (AUM) and GAE. For AUM, we design an Alternating-update-strategy to generate a new graph with reduced redundancy, in order to reduce the amount of redundant information that the encoder may capture. For GAE, we feed it the new graph and employ a re-mask decoding strategy to generate node representations. Our model is evaluated on five common real-world datasets for the node classification task, and the experimental results demonstrate its superiority. Meanwhile, our model has also achieved excellent results in specific e-commerce warehousing application scenarios. |
| Druh dokumentu: | Article |
| Jazyk: | English |
| ISSN: | 1460-2067 0010-4620 |
| DOI: | 10.1093/comjnl/bxaf007 |
| Rights: | OUP Standard Publication Reuse |
| Přístupové číslo: | edsair.doi...........6e9c8fdac0bd585e811db182c8bbdb8a |
| Databáze: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstrakt: | Self-supervised learning (SSL) has become a promising and popular learning paradigm for graph data, offering the advantage of capturing informative knowledge without reliance on manual labels. As a representative class of generative graph SSL models, existing graph autoencoders (GAE) excel in link prediction tasks and are steadily improving in node classification tasks. However, GAE is essentially based on the Information Maximization (InfoMax) principle, always captures much redundant information. In this paper, we propose an Alternating-update-strategy based Graph Autoencoder, including alternating update module (AUM) and GAE. For AUM, we design an Alternating-update-strategy to generate a new graph with reduced redundancy, in order to reduce the amount of redundant information that the encoder may capture. For GAE, we feed it the new graph and employ a re-mask decoding strategy to generate node representations. Our model is evaluated on five common real-world datasets for the node classification task, and the experimental results demonstrate its superiority. Meanwhile, our model has also achieved excellent results in specific e-commerce warehousing application scenarios. |
|---|---|
| ISSN: | 14602067 00104620 |
| DOI: | 10.1093/comjnl/bxaf007 |