针对异质图节点分类，提出自适应消息传递专家模型。
Mixture of Message Passing Experts with Routing Entropy Regularization for Node Classification
- 将消息传递拆分为传播与变换，由多专家网络协同处理
- 通过路由熵正则化实现软加权与软top-k路由动态调节
- 在12个基准数据集上超越当前最优方法，兼具可解释性
图神经网络（GNN）在图学习任务中取得显著进展，但在异质结构（连接节点特征与标签差异大）下性能常下降。为此，本文提出GNNMoE——一种基于熵驱动的混合消息传递专家框架，实现节点级自适应表征学习。GNNMoE将消息传递分解为传播与变换操作，通过多个专家网络结合混合路由机制实现整合；并引入路由熵正则化，动态调整软加权与软top-k路由，使模型能灵活适应多样化的邻域上下文。在12个基准数据集上的大量实验表明，GNNMoE持续优于现有最先进节点分类方法，同时保持可扩展性与可解释性。该工作为实现细粒度、个性化的节点表征学习提供了统一且原理清晰的方案。
原文摘要 · Abstract (English)
Graph neural networks (GNNs) have achieved significant progress in graph-based learning tasks, yet their performance often deteriorates when facing heterophilous structures where connected nodes differ substantially in features and labels. To address this limitation, we propose GNNMoE, a novel entropy-driven mixture of message-passing experts framework that enables node-level adaptive representation learning. GNNMoE decomposes message passing into propagation and transformation operations and integrates them through multiple expert networks guided by a hybrid routing mechanism. And a routing entropy regularization dynamically adjusts soft weighting and soft top-$k$ routing, allowing GNNMoE to flexibly adapt to diverse neighborhood contexts. Extensive experiments on twelve benchmark datasets demonstrate that GNNMoE consistently outperforms SOTA node classification methods, while maintaining scalability and interpretability. This work provides a unified and principled approach for achieving fine-grained, personalized node representation learning.
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。