https://jjcit.org/paper/282 10.5455/jjcit.71-1757505898 Yiming Zhao,Yongqing Wu Graph neural networks,Graph pre-training,Transfer learning,External attention 612 134 10-Sep.-2025 21-Nov.-2025, 10-Dec.-2025 and 13-Jan.-2026 14-Jan.-2026 This paper addresses the negative transfer problem in cross-domain graph pre-training under few-shot learning scenarios, it proposes a multi-component pre-training framework called Graph External Attention-enhanced Coordinators for Pre-training (GEA-CoPe). This framework integrates multi-head external attention with a graph coordinator. Tackling the structural and semantic discrepancies between cross-domain graphs is crucial for mitigating negative transfer; however, conventional methods often lack adaptability to complex, dynamic inter- domain variations and explicit constraints for intermediate feature-distribution consistency. The proposed framework leverages an external attention-based coordinator to mediate between different graph datasets, dynamically generating cross-graph semantic-alignment strategies to alleviate negative transfer induced by structural heterogeneity. It employs a dual-feature normalization strategy that incorporates a cross-layer distribution alignment loss on top of intra-layer node-similarity constraints, effectively suppressing feature drift. Furthermore, Kolmogorov-Arnold Networks (KANs) are introduced, whose parameter-adaptive activation functions better capture non-linear topological dependencies and enhance model interpretability. Experiments on ten real-world graph datasets demonstrate that GEA-CoPe exhibits superior cross-domain generalization capability and significantly improves performance in few-shot node classification tasks, with an average improvement of about 13.3% compared to other methods. The model can more accurately focus on critical graph structures, providing a theoretical foundation and practical paradigms for deploying graph neural networks in complex scenarios.