Interferometric Graph Transform for Community Labeling
This work addresses community labeling in graphs, which is important for network analysis applications, but appears incremental as it extends an existing transform.
The authors tackled unsupervised node representation learning for community graphs by extending the Interferometric Graph Transform (IGT) to community labeling, achieving state-of-the-art performance on datasets like Cora, Citeseer, Pubmed, and WikiCS.
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.