Mask-GVAE: Blind Denoising Graphs via Partition
arXiv:2102.04228 · doi:10.1145/3442381.3449899
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.
arXiv comment11 pages, 6 figures, 4 tables, In Proceedings of the Web Conference 2021
References in corpus (29)
- Modularity and community structure in networks
- Semi-Supervised Classification with Graph Convolutional Networks
- Categorical Reparameterization with Gumbel-Softmax
- Link communities reveal multiscale complexity in networks
- Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
- Simplifying Graph Convolutional Networks
- Adversarial Attacks on Neural Networks for Graph Data
- Certified Adversarial Robustness via Randomized Smoothing
- Random graphs with clustering
- Robustness of community structure in networks
- Constrained Graph Variational Autoencoders for Molecule Design
- Link Prediction Based on Graph Neural Networks
- Neural Combinatorial Optimization with Reinforcement Learning
- Graph Laplacian Regularization for Image Denoising: Analysis in the Continuous Domain
- Unsupervised speech representation learning using WaveNet autoencoders
- Subgraph Matching Kernels for Attributed Graphs
- GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders
- Supervised Community Detection with Line Graph Neural Networks
- Grammar Variational Autoencoder
- SpectralNet: Spectral Clustering using Deep Neural Networks
- Feature Graph Learning for 3D Point Cloud Denoising
- Estimation of Simultaneously Sparse and Low Rank Matrices
- Adversarial Attack on Community Detection by Hiding Individuals
- Denoising Criterion for Variational Auto-Encoding Framework
- Distortive Effects of Initial-Based Name Disambiguation on Measurements of Large-Scale Coauthorship Networks
- The DFS Fused Lasso: Linear-Time Denoising over General Graphs
- GAP: Generalizable Approximate Graph Partitioning Framework
- Unperturbed: spectral analysis beyond Davis-Kahan
- Dirichlet Graph Variational Autoencoder