受文化传播模型启发，新图神经网络可同时处理同质与异质关系。
Bridging Computational Social Science and Deep Learning: Cultural Dissemination-Inspired Graph Neural Networks
- 基于文化扩散模型设计相似性门控机制，自适应调节节点间信息交互
- 通过分段特征复制实现细粒度语义聚合，避免单一向量过度平滑
- 全局极化机制维持多类表示簇，适合复杂社交网络分析
图神经网络在文献分类、疫情预测、病毒营销、社交推荐和网络监控等场景中至关重要。然而其应用面临三大挑战：深层结构中的特征过度平滑、对异质关系处理能力差，以及整体特征聚合方式单一。为此，我们提出AxelGNN，该架构基于Axelrod的文化传播模型，包含三项创新：(1) 相似性门控交互，根据特征相似性自适应促进或抑制收敛；(2) 分段特征复制，实现语义特征组的细粒度聚合而非整体向量；(3) 全局极化机制，维持多个独立表示簇以防止过度平滑。实验表明，该模型能在单一架构内有效处理同质与异质图，无需根据图特性选择不同模型。在节点分类与影响力估计任务中，AxelGNN表现优于或媲美现有方法，且计算效率高。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。