mlsanityData to 7 Oct 2026

Graph Denoising with Framelet Regularizer

arXiv 2111.03264 ↗First posted 5 Nov 2021cs.LG cs.DMcited by 8

Not on the map. Why?

Abstract (arXiv)

As graph data collected from the real world is merely noise-free, a practical representation of graphs should be robust to noise. Existing research usually focuses on feature smoothing but leaves the geometric structure untouched. Furthermore, most work takes L2-norm that pursues a global smoothness, which limits the expressivity of graph neural networks. This paper tailors regularizers for graph data in terms of both feature and structure noises, where the objective function is efficiently solved with the alternating direction method of multipliers (ADMM). The proposed scheme allows to take multiple layers without the concern of over-smoothing, and it guarantees convergence to the optimal solutions. Empirical study proves that our model achieves significantly better performance compared with popular graph convolutions even when the graph is heavily contaminated.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 35 of its 67 references that are in the map. First posted on arXiv 5 Nov 2021.

Builds on

35 of 67 references.

References · 35

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2018How Powerful are Graph Neural Networks?cited by 4,355
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  6. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  7. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  8. 2019Simplifying Graph Convolutional Networkscited by 1,470
  9. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  10. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  11. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  12. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
23 more
  1. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  2. 2017Graph Signal Processing: Overview, Challenges and Applicationscited by 409
  3. 2018Deep Learning on Graphs: A Surveycited by 393
  4. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  5. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 260
  6. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 253
  7. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  8. 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
  9. 2020Higher-Order Explanations of Graph Neural Networks via Relevant Walkscited by 138
  10. 2019Graph Wavelet Neural Networkcited by 131
  11. 2021Interpreting and Unifying Graph Neural Networks with An Optimization Frameworkcited by 131
  12. 2019LanczosNet: Multi-Scale Deep Graph Convolutional Networkscited by 73
  13. 2021Elastic Graph Neural Networkscited by 67
  14. 2021How Framelets Enhance Graph Neural Networkscited by 46
  15. 2014Trend Filtering on Graphscited by 45
  16. 2016Autoregressive Moving Average Graph Filteringcited by 35
  17. 2020Graph Unrolling Networks: Interpretable Neural Networks for Graph Signal Denoisingcited by 33
  18. 2020Co-embedding of Nodes and Edges with Graph Neural Networkscited by 30
  19. 2017Design of graph filters and filterbankscited by 22
  20. 2019Differentiable Linearized ADMMcited by 18
  21. 2013Parallel Multi-Block ADMM with o(1/k) Convergencecited by 12
  22. 2020Understanding Graph Neural Networks from Graph Signal Denoising Perspectivescited by 11
  23. 2021BiGCN: A Bi-directional Low-Pass Filtering Graph Neural Networkcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 4; 2024: 1.

8 papers.

  1. 2023How Curvature Enhance the Adaptation Power of Framelet GCNscited by 13
  2. 2022Generalized energy and gradient flow via graph frameletscited by 10
  3. 2022Robust Graph Representation Learning for Local Corruption Recoverycited by 6
  4. 2023Framelet Message Passingcited by 3
  5. 2022How Powerful is Implicit Denoising in Graph Neural Networkscited by 2
  6. 2023Frameless Graph Knowledge Distillationcited by 2
  7. 2023Revisiting Generalized p-Laplacian Regularized Framelet GCNs: Convergence, Energy Dynamic and Training with Non-Linear Diffusioncited by 1
  8. 2024Graph Adversarial Diffusion Convolutioncited by 0