全球导航卫星系统（GNSS）正面临日益加剧的故意干扰威胁，严重削弱了依赖高精度定位与授时的关键基础设施。当前的位置误差校正（PEC）方法主要集中于多径传播误差，未能充分利用卫星星座所具有的时空一致性。本文将干扰抑制问题重构为动态图回归任务，提出接收端中心化的深度时序图网络——Jamming Guardian（JaGuard），用于在固定位置（如路侧单元）估计并校正干扰引发的位置漂移。该方法将卫星-接收机场景建模为每秒1帧（1 Hz epoch）的异构星型图；其核心模块——异构图卷积LSTM（Heterogeneous Graph ConvLSTM）融合空间上下文（信噪比SNR、方位角、仰角）与短期时间动态，以预测二维位置偏差。在包含两类商用接收机实测数据的真实世界数据集上（施加合成射频干扰，涵盖三种干扰器类型，功率范围−45至−70 dBm），JaGuard在所有先进基线方法中持续取得最低的平均绝对误差（MAE）。在强干扰条件（−45 dBm）下，其MAE维持于2.85–5.92 cm；干扰减弱后进一步提升至亚2 cm水平。在混合功率干扰数据集上，JaGuard亦全面超越所有基线：GP01接收机MAE为2.26 cm，U-blox 10接收机MAE为2.61 cm。即使训练数据极度匮乏（仅10%），JaGuard仍保持稳定，误差被约束于15–20 cm范围内，且未出现基线方法中显著的方差激增现象。结果证实，对星座图物理退化过程进行动态建模，是实现鲁棒干扰校正的必要条件。

Global Navigation Satellite Systems (GNSS) face growing disruption from intentional jamming, undermining critical infrastructure where precise positioning and timing are essential. Current position error correction (PEC) methods mainly focus on multi-path propagation errors and fail to exploit the spatio-temporal coherence of satellite constellations. We recast jamming mitigation as a dynamic graph regression problem. We propose Jamming Guardian (JaGuard), a receiver-centric deep temporal graph network that estimates and corrects jamming-induced positional drift at fixed locations like roadside units. Modeling the satellite-receiver scene as a heterogeneous star graph at each 1 Hz epoch, our Heterogeneous Graph ConvLSTM fuses spatial context (SNR, azimuth, elevation) with short-term temporal dynamics to predict 2D positional deviation. Evaluated on a real-world dataset from two commercial receivers under synthesized RF interference (three jammer types, -45 to -70 dBm), JaGuard consistently yields the lowest Mean Absolute Error (MAE) compared to advanced baselines. Under severe jamming (-45 dBm), it maintains an MAE of 2.85-5.92 cm, improving to sub-2 cm at lower interference. On mixed-power datasets, JaGuard surpasses all baselines with MAEs of 2.26 cm (GP01) and 2.61 cm (U-blox 10). Even under extreme data starvation (10% training data), JaGuard remains stable, bounding error at 15-20 cm and preventing the massive variance increase seen in baselines. This confirms that dynamically modeling the physical deterioration of the constellation graph is strictly necessary for resilient interference correction.