AI 中文总结
研究图压缩中粗化和稀疏化两种范式对信号传播行为的影响，通过三个指标在五个数据集等多种条件下测量，发现两者在保留信号多样性和传播保真度上存在矛盾，强调需联合考虑两维度的评估协议。
AI 中文摘要
图压缩降低了图学习的计算成本，但其对信号传播的影响在很大程度上仍未得到充分探索。现有工作通过下游任务性能或结构保留来评估压缩，而这两者都无法直接捕捉压缩后传播动态的变化。我们研究了两种基本的压缩范式，粗化和稀疏化，并探讨它们是否保留原始图的传播行为。在五个数据集、不同压缩率和传播深度的情况下，我们通过三个互补指标测量信号行为。结果揭示了这两种压缩方法之间的持续矛盾。稀疏化保留了更高的信号多样性并减轻了过度平滑，但它的传播轨迹逐渐偏离原始图。粗化更忠实地保留传播行为，但代价是更强的平滑和秩崩溃。这些发现表明，在图压缩下，两个以传播为中心的目标，即保留信号多样性和保留传播保真度，是不同的且在经验上相互矛盾，突出了联合考虑这两个维度的评估协议的必要性。代码和结果可在该https网址获取。
英文摘要
Graph compression reduces the computational cost of graph learning, but its effect on signal propagation remains largely underexplored. Existing work evaluates compression through downstream task performance or structural preservation, neither of which directly captures how propagation dynamics change after compression. We study two fundamental compression paradigms, coarsening and sparsification, and ask whether they preserve the propagation behavior of the original graph. Across five datasets, varying compression rates, and propagation depths, we measure signal behavior through three complementary metrics. Our results reveal a consistent tension between the two compression families. Sparsification retains higher signal diversity and mitigates oversmoothing, but its propagation trajectory progressively diverges from that of the original graph. Coarsening more faithfully preserves propagation behavior, but at the cost of stronger smoothing and rank collapse. These findings demonstrate that two propagation-centric objectives, preserving signal diversity and preserving propagation fidelity, are distinct and empirically at odds under graph compression, highlighting the need for evaluation protocols that jointly consider both dimensions. The code and results are available at: https://github.com/KawshikBanerjee/Compression-Propagation-Duality
