mlsanityData to 7 Oct 2026

Graph Adversarial Diffusion Convolution

arXiv 2406.02059 ↗First posted 4 Jun 2024cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper introduces a min-max optimization formulation for the Graph Signal Denoising (GSD) problem. In this formulation, we first maximize the second term of GSD by introducing perturbations to the graph structure based on Laplacian distance and then minimize the overall loss of the GSD. By solving the min-max optimization problem, we derive a new variant of the Graph Diffusion Convolution (GDC) architecture, called Graph Adversarial Diffusion Convolution (GADC). GADC differs from GDC by incorporating an additional term that enhances robustness against adversarial attacks on the graph structure and noise in node features. Moreover, GADC improves the performance of GDC on heterophilic graphs. Extensive experiments demonstrate the effectiveness of GADC across various datasets. Code is available at https://github.com/SongtaoLiu0823/GADC.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 45 of its 62 references that are in the map. First posted on arXiv 4 Jun 2024.

Builds on

45 of 62 references.

References · 45

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  6. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  7. 2019Simplifying Graph Convolutional Networkscited by 1,470
  8. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  9. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  10. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  11. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  12. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
33 more
  1. 2019Diffusion Improves Graph Learningcited by 414
  2. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  3. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  4. 2018Adversarial Attack on Graph Structured Datacited by 300
  5. 2019PairNorm: Tackling Oversmoothing in GNNscited by 297
  6. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
  7. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 260
  8. 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
  9. 2021Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillationcited by 151
  10. 2022NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphscited by 137
  11. 2020A Unified View on Graph Neural Networks as Graph Signal Denoisingcited by 110
  12. 2020Retrosynthesis Prediction with Conditional Graph Logic Networkcited by 103
  13. 2021Robustness of Graph Neural Networks at Scalecited by 100
  14. 2021Elastic Graph Neural Networkscited by 67
  15. 2021Graph Neural Networks Inspired by Classical Iterative Algorithmscited by 60
  16. 2019Certifiable Robustness and Robust Training for Graph Convolutional Networkscited by 59
  17. 2021Dissecting the Diffusion Process in Linear Graph Convolutional Networkscited by 58
  18. 2019Label Efficient Semi-Supervised Learning via Graph Filteringcited by 46
  19. 2023Are Defenses for Graph Neural Networks Robust?cited by 38
  20. 2022Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNNcited by 34
  21. 2020Graph Unrolling Networks: Interpretable Neural Networks for Graph Signal Denoisingcited by 33
  22. 2022Optimization-Induced Graph Implicit Nonlinear Diffusioncited by 28
  23. 2023Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directionscited by 28
  24. 2022EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networkscited by 26
  25. 2023Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approachcited by 24
  26. 2021A Unifying Generative Model for Graph Learning Algorithms: Label Propagation, Graph Convolutions, and Combinationscited by 18
  27. 2022Improving Out-of-Distribution Generalization by Adversarial Training with Structured Priorscited by 17
  28. 2021Graph Structural Attack by Perturbing Spectral Distancecited by 16
  29. 2021Adversarial Attack Framework on Graph Embedding Models with Limited Knowledgecited by 10
  30. 2021Graph Denoising with Framelet Regularizercited by 8
  31. 2023Adversarially Robust Neural Architecture Search for Graph Neural Networkscited by 7
  32. 2022How Powerful is Implicit Denoising in Graph Neural Networkscited by 2
  33. 2023Towards Deep Learning Models Resistant to Transfer-based Adversarial Attacks via Data-centric Robust Learningcited by 2

Built on by

Not cited yet.