不仅仅是过度平滑：检测图神经网络中的回声室效应
Not Just Oversmoothing: Detecting the Echo Chamber Effect in Graph Neural Networks
- University of Melbourne（墨尔本大学）
- Australian National University（澳大利亚国立大学）
- Data61, CSIRO（联邦科学与工业研究组织Data61研究院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对图神经网络中社区内表示快速坍缩而社区间分离持续存在的回声室效应，提出回声室指数（ECI）进行量化，并设计轻量级插件CASP解耦社区内外聚合以提升分类性能。
AI中文摘要：
过度平滑是图神经网络（GNNs）一个众所周知的失效模式。然而，大多数现有的诊断方法依赖于全局聚合度量，这些度量无法捕捉消息传递的异质动态。真实世界的图展现出显著的社区结构，消息传递在两个时间尺度上运行，表示在社区内迅速坍缩，而在社区间则缓慢坍缩。这造成了一个关键缺口，即社区内表示可能变得难以区分，而社区间分离持续存在，我们将这种失效模式称为回声室效应。为了量化这一效应，我们引入了回声室指数（ECI），该指数按社区成员关系对成对距离进行分层，并揭示全局能量减弱而社区间分离持续存在的情况。ECI进一步表明，特征保留机制在我们的理论分析条件下可以维持回声室。其后果取决于标签结构：当社区与类别对齐时，回声室可以锐化节点分类；而当它们不对齐时，同样的坍缩使得分类在理论上更加困难。基于这一分析，我们提出了社区感知分裂传播（CASP），这是一种轻量级插件，它解耦了社区内和社区间的聚合，并从标签结构中学习它们的平衡。CASP在大多数评估的同质和异质设置中提升了多种骨干GNN的性能。
英文摘要：
Oversmoothing is a well-known failure mode of Graph Neural Networks (GNNs). However, most existing diagnostics rely on global aggregation measures that fail to capture the heterogeneous dynamics of message passing. Real-world graphs exhibit pronounced community structure, and message passing operates on two timescales, with representations collapsing rapidly within communities and slowly across them. This creates a critical gap in which intra-community representations can become indistinguishable while inter community separation persists, a failure mode that we refer to as the Echo Chamber Effect. To quantify this effect, we introduce the Echo Chamber Index (ECI), which stratifies pairwise distances by community membership and reveals when global energy diminishes while inter-community separation persists. ECI further shows that feature retention mechanisms can preserve the echo chamber under the conditions of our theoretical analysis. The consequences depend on label structure: when communities align with classes, the echo chamber can sharpen node classification, whereas when they do not, the same collapse makes classification provably harder. Motivated by this analysis, we propose Community-Aware Split Propagation (CASP), a lightweight plugin that decouples intra- and inter-community aggregation and learns their balance from label structure. CASP improves diverse backbone GNNs across most evaluated homophilic and heterophilic settings.
