Interferometric Graph Transform for Community Labeling
arXiv:2106.05875
Abstract
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.
References in corpus (18)
- Adam: A Method for Stochastic Optimization
- Inductive Representation Learning on Large Graphs
- Geometric deep learning: going beyond Euclidean data
- Spectral Networks and Locally Connected Networks on Graphs
- Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
- DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
- Stability Properties of Graph Neural Networks
- GMNN: Graph Markov Neural Networks
- Universal Invariant and Equivariant Graph Neural Networks
- Supervised Community Detection with Line Graph Neural Networks
- Learning Graph Representations with Embedding Propagation
- Tackling Over-Smoothing for General Graph Convolutional Networks
- Joint Time-Frequency Scattering for Audio Classification
- Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks
- Compressing the Input for CNNs with the First-Order Scattering Transform
- Deep Learning by Scattering
- Graph and graphon neural network stability
- Interferometric Graph Transform: a Deep Unsupervised Graph Representation