Multilevel Graph Wavelet Compressed Sensing with Scale-Aware Neural Recovery

• URL: http://arxiv.org/abs/2607.20857v1
• Date: Thu, 23 Jul 2026 02:26:51 GMT
• Title: Multilevel Graph Wavelet Compressed Sensing with Scale-Aware Neural Recovery
• Abstract summary: We propose Graph Wavelet Compressed Sensing (GWCS), a learning-based framework for offline compression of graph signals.<n>GWCS represents graph signals as sparse, interpretable wavelet-domain representations using the spectral graph wavelet transform.<n>We evaluate the proposed framework on synthetic approximately band-limited graph signals over random graphs and four PDE simulation datasets over meshes.
• Score: 3.056767395680581
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scientific machine learning methods such as neural operators and physics-informed neural networks have advanced engineering applications and inverse problems, but their training typically requires large volumes of simulated data. This makes data preparation and model training expensive. We propose Graph Wavelet Compressed Sensing (GWCS), a learning-based framework for offline compression of graph signals by representing them as sparse, interpretable wavelet-domain representations using the spectral graph wavelet transform. The framework combines a nonparametric multilevel importance sampler, which retains high-energy wavelet coefficients within each scale for a given compression ratio, with a scale-aware graph neural network that reconstructs the signal from the sparse coefficients. We evaluate the proposed framework on synthetic approximately band-limited graph signals over random graphs and four PDE simulation datasets over meshes, which include Turbulent Radiative Layer, Viscoelastic Instability, Kolmogorov Flow, and Dynamic Stall. We compare against graph signal sampling methods and graph autoencoder baselines. Results demonstrate that the framework achieves high reconstruction fidelity and substantial data compression compared to existing benchmarks.

Related papers

• Generative Diffusion Models of Stochastic Graph Signals [74.4097723209053]
  This paper tackles problems of conditional graph signal generative modeling and tackles them with a single denoising diffusion framework.<n>We learn a reverse diffusion process, parametrized by graph neural networks (GNNs), that draws graph signals conditioned directly on the graph topology and on node-feature side information.<n>We demonstrate our method on two generative tasks: stock price forecasting and optimal wireless resource allocation, with extensive numerical results in both domains.
  arXiv  Detail & Related papers  (2026-07-07T22:02:13Z)
• Graph Signal Generative Diffusion Models [74.75869068073577]
  We introduce U-shaped encoder-decoder graph neural networks (U-GNNs) for graph signal generation using denoising diffusion processes.<n>The architecture learns node features at different resolutions with skip connections between the encoder and decoder paths.<n>We demonstrate the effectiveness of the diffusion model in probabilistic forecasting of stock prices.
  arXiv  Detail & Related papers  (2025-09-21T21:57:27Z)
• Beyond Neural Networks: Symbolic Reasoning over Wavelet Logic Graph Signals [0.0]
  We present a fully non neural learning framework based on Graph Laplacian Wavelet Transforms (GLWT)<n>Our model operates purely in the graph spectral domain using structured multiscale filtering, nonlinear shrinkage, and symbolic logic over wavelet coefficients.
  arXiv  Detail & Related papers  (2025-07-27T19:01:13Z)
• SlepNet: Spectral Subgraph Representation Learning for Neural Dynamics [5.424636897130673]
  Graph neural networks have been useful in machine learning on graph-structured data.<n>They have had limited use in representing patterning signals over graphs.<n>SlepNet is a novel GCN that uses Slepian bases rather than graph harmonics.
  arXiv  Detail & Related papers  (2025-06-19T21:03:52Z)
• Learning Graph Structure from Convolutional Mixtures [119.45320143101381]
  We propose a graph convolutional relationship between the observed and latent graphs, and formulate the graph learning task as a network inverse (deconvolution) problem. In lieu of eigendecomposition-based spectral methods, we unroll and truncate proximal gradient iterations to arrive at a parameterized neural network architecture that we call a Graph Deconvolution Network (GDN) GDNs can learn a distribution of graphs in a supervised fashion, perform link prediction or edge-weight regression tasks by adapting the loss function, and they are inherently inductive.
  arXiv  Detail & Related papers  (2022-05-19T14:08:15Z)
• Spectral Graph Convolutional Networks With Lifting-based Adaptive Graph Wavelets [81.63035727821145]
  Spectral graph convolutional networks (SGCNs) have been attracting increasing attention in graph representation learning. We propose a novel class of spectral graph convolutional networks that implement graph convolutions with adaptive graph wavelets.
  arXiv  Detail & Related papers  (2021-08-03T17:57:53Z)
• How Framelets Enhance Graph Neural Networks [27.540282741523253]
  This paper presents a new approach for assembling graph neural networks based on framelet transforms. We propose shrinkage as a new activation for the framelet convolution, which thresholds the high-frequency information at different scales.
  arXiv  Detail & Related papers  (2021-02-13T19:19:19Z)
• Decimated Framelet System on Graphs and Fast G-Framelet Transforms [3.7277730514654555]
  An adequate representation of graph data is vital to the learning performance of a statistical or machine learning model for graph-structured data. We propose a novel multiscale representation system for graph data, called decimated framelets, which form a localized tight frame on the graph. The effectiveness is demonstrated by real-world applications, including multiresolution analysis for traffic network, and graph neural networks for graph classification tasks.
  arXiv  Detail & Related papers  (2020-12-12T23:57:17Z)
• Unrolling of Deep Graph Total Variation for Image Denoising [106.93258903150702]
  In this paper, we combine classical graph signal filtering with deep feature learning into a competitive hybrid design. We employ interpretable analytical low-pass graph filters and employ 80% fewer network parameters than state-of-the-art DL denoising scheme DnCNN.
  arXiv  Detail & Related papers  (2020-10-21T20:04:22Z)
• Data-Driven Learning of Geometric Scattering Networks [74.3283600072357]
  We propose a new graph neural network (GNN) module based on relaxations of recently proposed geometric scattering transforms. Our learnable geometric scattering (LEGS) module enables adaptive tuning of the wavelets to encourage band-pass features to emerge in learned representations.
  arXiv  Detail & Related papers  (2020-10-06T01:20:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.