In this work, we study the behavior of standard models for community detection under spectral manipulations. Through various ablation experiments, we evaluate the impact of bandpass filtering on the performance of a GCN: we empirically show that most of the necessary and used information for nodes classification is contained in the low-frequency domain, and thus contrary to images, high frequencies are less crucial to community detection. In particular, it is sometimes possible to obtain accuracies at a state-of-the-art level with simple classifiers that rely only on a few low frequencies.

中文翻译：

---

GCN 拉普拉斯算子的低秩预测

在这项工作中，我们研究了光谱操作下社区检测的标准模型的行为。通过各种消融实验，我们评估了带通滤波对 GCN 性能的影响：我们凭经验表明，节点分类所需和使用的大部分信息都包含在低频域中，因此与图像相反，高频对社区检测不太重要。特别是，有时可以使用仅依赖少数低频的简单分类器在最先进的水平上获得准确度。