PreGS：一种基于参数迁移的多专家图神经网络用于节点分类
PreGS: A Parameter-Transfer-Based Multi-Expert Graph Neural Network for Node Classification
浏览论文内容
中文总结 AI 辅助
本文提出PreGS框架，通过参数迁移将预训练GAT的权重传给多个GraphSAGE专家，融合多源特征进行节点分类，并扩展出PreGSv2，在八个数据集上验证了其有效性和稳定性。
中文摘要 AI 辅助
图神经网络通过聚合图邻域信息在节点分类中取得了强劲的性能。然而，单一的聚合机制可能不足以捕获跨图数据集的多样化结构模式。此外，独立训练多个结构分支可能会引入大量开销，且不一定能产生稳定的节点表示。为解决这些问题，本文提出了PreGS，一种基于参数迁移的多专家图神经网络框架。PreGS首先预训练一个多头图注意力网络（GAT），并将其第一层注意力头的线性变换权重迁移到多个GraphSAGE专家中。迁移后的专家被冻结，用作互补的结构分支。融合后的原始节点特征、GAT头表示和GraphSAGE专家表示被输入到一个多层感知机（MLP）中，其输出进一步与预训练的GAT逻辑值融合。基于PreGS，我们进一步开发了PreGSv2，它引入了源级加权和结构门控机制，用于自适应多源特征集成。在八个公开图数据集上的实验表明，PreGS和PreGSv2相对于代表性的图神经网络基线取得了有竞争力的性能。消融、参数迁移、敏感性、聚合器、可视化和训练时间分析进一步验证了所提出框架的有效性和稳定性。代码和数据集可在该https URL获取。
英文摘要
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) and transfers the linear transformation weights of its first-layer attention heads to multiple GraphSAGE experts. The transferred experts are frozen and used as complementary structural branches. The fused raw node features, GAT head representations, and GraphSAGE expert representations are fed into a multilayer perceptron (MLP), whose output is further fused with the pretrained GAT logits. Based on PreGS, we further develop PreGSv2, which introduces source-level weighting and a structural gating mechanism for adaptive multi-source feature integration. Experiments on eight public graph datasets show that PreGS and PreGSv2 achieve competitive performance against representative graph neural network baselines. Ablation, parameter-transfer, sensitivity, aggregator, visualization, and training-time analyses further validate the effectiveness and stability of the proposed framework. The code and datasets are available at https://github.com/LH-Czc/PreGS.
发表机构
- College of Physics and Information Engineering, Minnan Normal University（闽南师范大学物理与信息工程学院）
机构由 AI 辅助整理，请以论文原文为准。
