mlsanityData to 14 Oct 2026

On the Impact of Downstream Tasks on Sampling and Reconstructing Noisy Graph Signals

arXiv 2509.10874 ↗First posted 13 Sep 2025eess.SP cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We investigate graph signal reconstruction and sample selection for classification tasks. We present general theoretical characterisations of classification error applicable to multiple commonly used reconstruction methods, and compare that to the classical reconstruction error. We demonstrate the applicability of our results by using them to derive new optimal sampling methods for linearized graph convolutional networks, and show improvement over other graph signal processing based methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 43 references that are in the map. First posted on arXiv 13 Sep 2025.

Builds on

27 of 43 references.

References · 27

  1. 2017Inductive Representation Learning on Large Graphscited by 6,320
  2. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  3. 2019Simplifying Graph Convolutional Networkscited by 1,477
  4. 2017Graph Signal Processing: Overview, Challenges and Applicationscited by 413
  5. 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
  6. 2020Handling Missing Data with Graph Representation Learningcited by 133
  7. 2024Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classificationcited by 85
  8. 2021On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Featurescited by 63
  9. 2019Missing Data Imputation with Adversarially-trained Graph Convolutional Networkscited by 54
  10. 2020Graph Convolutional Networks for Graphs Containing Missing Featurescited by 47
  11. 2020Learning on Attribute-Missing Graphscited by 42
  12. 2023Graph Neural Networks with Learnable and Optimal Polynomial Basescited by 36
15 more
  1. 2015Discrete Signal Processing on Graphs: Sampling Theorycited by 34
  2. 2014Matrix Completion on Graphscited by 26
  3. 2020Gaussian Processes on Graphs via Spectral Kernel Learningcited by 24
  4. 2020Incomplete Graph Representation and Learning via Partial Graph Neural Networkscited by 16
  5. 2015Random sampling of bandlimited signals on graphscited by 15
  6. 2017Greedy Sampling of Graph Signalscited by 9
  7. 2023On Manipulating Signals of User-Item Graph: A Jacobi Polynomial-based Graph Collaborative Filteringcited by 9
  8. 2019Fast Graph Sampling Set Selection Using Gershgorin Disc Alignmentcited by 8
  9. 2021Practical graph signal sampling with log-linear size scalingcited by 5
  10. 2017Graph sampling with determinantal processescited by 4
  11. 2018Low-complexity Graph Sampling with Noise and Signal Reconstruction via Neumann Seriescited by 4
  12. 2018A-Optimal Sampling and Robust Reconstruction for Graph Signals via Truncated Neumann Seriescited by 3
  13. 2024Towards joint graph learning and sampling set selection from datacited by 2
  14. 2024On the Impact of Sample Size in Reconstructing Noisy Graph Signals: A Theoretical Characterisationcited by 1
  15. 2024Graph-Based Signal Sampling with Adaptive Subspace Reconstruction for Spatially-Irregular Sensor Datacited by 1

Built on by

Not cited yet.