Interferometric Graph Transform for Community Labeling

2021/06/04 by Nathan Grinsztajn, Louis Leconte, Grinsztajn, Nathan +4
Biochemistry, Genetics and Molecular Biology · Computer Science · Physics and Astronomy · #Advanced Graph Neural Networks #Bioinformatics and Genomic Networks #Complex Network Analysis Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2106.05875

openalex publication_date 2021/06/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Adam: A Method for Stochastic Optimization
• Wavelets on graphs via spectral graph theory
• Geometric Deep Learning: Going beyond Euclidean data
• Inductive Representation Learning on Large Graphs
• Supervised Community Detection with Line Graph Neural Networks
• Universal Invariant and Equivariant Graph Neural Networks
• GMNN: Graph Markov Neural Networks
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories
• DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
• Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks
• Tackling Over-Smoothing for General Graph Convolutional Networks

Related

• Classic Graph Structural Features Outperform Factorization-Based Graph Embedding Methods on Community Labeling
• vGraph: A Generative Model for Joint Community Detection and Node Representation Learning
• A Unified Framework for Community Detection and Network Representation Learning
• A Boosting Approach to Learning Graph Representations
• Expanding Label Sets for Graph Convolutional Networks