We present a new approach for learning unsupervised node representations in community graphs. We significantly extend the Interferometric Graph Transform (IGT) to community labeling: this non-linear operator iteratively extracts features that take advantage of the graph topology through demodulation operations. An unsupervised feature extraction step cascades modulus non-linearity with linear operators that aim at building relevant invariants for community labeling. Via a simplified model, we show that the IGT concentrates around the E-IGT: those two representations are related through some ergodicity properties. Experiments on community labeling tasks show that this unsupervised representation achieves performances at the level of the state of the art on the standard and challenging datasets Cora, Citeseer, Pubmed and WikiCS.

中文翻译：

---

社区标记的干涉图变换

我们提出了一种在社区图中学习无监督节点表示的新方法。我们将干涉图变换 (IGT) 显着扩展到社区标记：这种非线性算子通过解调操作迭代地提取利用图拓扑的特征。无监督特征提取步骤将模非线性与旨在为社区标记构建相关不变量的线性算子级联。通过一个简化的模型，我们表明 IGT 集中在 E-IGT 周围：这两种表示通过一些遍历性属性相关联。社区标记任务的实验表明，这种无监督表示在标准和具有挑战性的数据集 Cora、Citeseer、Pubmed 和 WikiCS 上达到了最先进水平的性能。