Mask-GVAE: Blind Denoising Graphs via Partition

Abstract

We present Mask-GVAE, a variational generative model for blind denoising large discrete graphs, in which "blind denoising" means we don't require any supervision from clean graphs. We focus on recovering graph structures via deleting irrelevant edges and adding missing edges, which has many applications in real-world scenarios, for example, enhancing the quality of connections in a co-authorship network. Mask-GVAE makes use of the robustness in low eigenvectors of graph Laplacian against random noise and decomposes the input graph into several stable clusters. It then harnesses the huge computations by decoding probabilistic smoothed subgraphs in a variational manner. On a wide variety of benchmarks, Mask-GVAE outperforms competing approaches by a significant margin on PSNR and WL similarity.

11 pages, 6 figures, 4 tables, In Proceedings of the Web Conference 2021

References in corpus (14)

• Modularity and community structure in networks
• Semi-Supervised Classification with Graph Convolutional Networks
• Simplifying Graph Convolutional Networks
• Certified Adversarial Robustness via Randomized Smoothing
• Random graphs with clustering
• Robustness of community structure in networks
• Neural Combinatorial Optimization with Reinforcement Learning
• Subgraph Matching Kernels for Attributed Graphs
• Grammar Variational Autoencoder
• Adversarial Attack on Community Detection by Hiding Individuals
• Distortive Effects of Initial-Based Name Disambiguation on Measurements of Large-Scale Coauthorship Networks
• GAP: Generalizable Approximate Graph Partitioning Framework
• Unperturbed: spectral analysis beyond Davis-Kahan
• Dirichlet Graph Variational Autoencoder