Low-Rank Projections of GCNs Laplacian
This work addresses community detection in graph data, showing incremental insights by revealing the spectral properties of GCNs for node classification.
The paper tackled the problem of community detection with graph convolutional networks (GCNs) by analyzing spectral manipulations, finding that low-frequency information is crucial and high frequencies are less important, enabling state-of-the-art accuracy with simple classifiers using only a few low frequencies.
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.