AI 中文总结
本文构建同质图回归合成基准，解耦标签噪声与特征分布偏移，通过41种配置410次实验发现GNN对中等标签扰动容忍度高，但极端分布偏移导致性能大幅退化，为部署监控提供基线。
AI 中文摘要
数据质量是图神经网络（GNNs）在真实世界图挖掘任务中可靠部署的主要瓶颈。在各种退化来源中，标签噪声和特征分布偏移（以下简称分布偏移）是两种常见但根本不同的挑战。为了在受控条件下研究它们的影响，本文构建了一个同质图回归的合成基准，其中这两个因素可以被独立操控。共进行了41种配置和410次运行，以评估代表性GNN模型在不同噪声和偏移条件下的行为。结果显示了两种不同的模式。首先，在加性标签损坏下，性能在广泛的噪声设置范围内保持相对稳定，仅在观察到约50%噪声比率的转变区域后才开始急剧恶化。其次，在极端特征分布偏移下，所有测试模型都遭受了显著退化，测试MSE增加了48倍到316倍，相关性下降了73%到89%。这些发现表明，在当前受控设置中，GNNs对中等程度的标签扰动比对严重的分布不匹配具有明显更高的容忍度。该研究为理解数据质量如何影响基于GNN的图挖掘系统提供了受控的经验基线，并为面向部署的监控和模型维护提供了实际意义。
英文摘要
Data quality is a major bottleneck for the reliable deployment of graph neural networks (GNNs) in real-world graph mining tasks. Among various sources of degradation, label noise and feature distribution shift (hereafter referred to as distribution shift) are two common yet fundamentally different challenges. To study their effects under controlled conditions, this paper constructs a synthetic homophilic graph regression benchmark in which the two factors can be manipulated separately. A total of 41 configurations and 410 runs are conducted to evaluate the behavior of representative GNN models under varying noise and shift conditions. The results show two distinct patterns. First, under additive label corruption, performance remains relatively stable over a broad range of noise settings and begins to deteriorate sharply only after an observed transition region around the 50 percent noise ratio. Second, under extreme feature distribution shift, all tested models suffer substantial degradation, with test MSE increasing by 48 times to 316 times and correlation dropping by 73 percent to 89 percent. These findings suggest that, in the present controlled setting, GNNs are considerably more tolerant to moderate label perturbation than to severe distribution mismatch. The study provides a controlled empirical baseline for understanding how data quality affects GNN-based graph mining systems and offers practical implications for deployment-oriented monitoring and model maintenance.
CommentsAccepted by ICCCBDA 2026
