SOURCE-LINKED INTELLIGENCE

PreGS: A Parameter-Transfer-Based Multi-Expert Graph Neural Network for Node Classification

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

Graph neural networks have achieved strong performance in node classification by aggregating information from graph neighborhoods. However, a single aggregation mechanism may be insufficient to capture diverse structural patterns across graph datasets. Moreover, independently training multiple structural branches can introduce substantial overhead without necessarily producing stable node representations. To address these issues, this paper proposes PreGS, a parameter-transfer-based multi-expert graph neural network framework. PreGS first pretrains a multi-head graph attention network (GAT) an

Read original source ↗ Open in workspace

recordType

paper

region

Global