连接计算社会科学与深度学习：基于文化传播的图神经网络
Bridging Computational Social Science and Deep Learning: Cultural Dissemination-Inspired Graph Neural Networks
AI总结：
AxelGNN通过融合文化传播模型，解决图神经网络在处理同质与异质图时的过平滑问题，实现高效且通用的图学习方法。
摘要：
图神经网络（GNNs）已成为在引用网络中的文档分类、流行病预测、病毒营销、社交网络中的用户推荐和网络监控等应用中至关重要的技术。然而，其部署面临三个关键挑战：深度架构中的特征过平滑、对异质关系处理不佳以及单一特征聚合。为解决这些问题，我们引入了AxelGNN，这是一种基于Axelrod文化传播模型的新型架构，集成了三个关键创新：（1）相似性门控交互，可根据特征相似性自适应地促进收敛或发散；（2）分段特征复制，使能够对语义特征组进行细粒度聚合，而不是单一向量；（3）全局极化，维持多个不同的表示簇以防止过平滑。该模型实证表明，其能够在单一架构中处理同质和异质图，而无需根据图特性专门选择模型。我们的实验表明，AxelGNN在节点分类和影响估计方面实现了与现有方法相当或更优的性能，同时保持了计算效率。
英文摘要：
Graph Neural Networks (GNNs) have become vital in applications like document classification in citation networks, epidemic forecasting, viral marketing, user recommendation in social networks, and network monitoring. However, their deployment faces three key challenges: feature oversmoothing in deep architectures, poor handling of heterogeneous relationships, and monolithic feature aggregation. To address these, we introduce AxelGNN, a novel architecture based on Axelrod's cultural dissemination model that incorporates three key innovations: (1) similarity-gated interactions that adaptively promote convergence or divergence based on feature similarity, (2) segment-wise feature copying that enables fine-grained aggregation of semantic feature groups rather than monolithic vectors, and (3) global polarization that maintains multiple distinct representation clusters to prevent oversmoothing. This model demonstrates empirically the capability to handle both homophilic and heterophilic graphs within a single architecture, without requiring specialized model selection based on graph characteristics. Our experiments demonstrate that AxelGNN achieves competitive or superior performance compared to existing methods in node classification and influence estimation while maintaining computational efficiency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
