mlsanityData to 7 Oct 2026

How Powerful is Implicit Denoising in Graph Neural Networks

arXiv 2209.14514 ↗First posted 29 Sep 2022cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs), which aggregate features from neighbors, are widely used for graph-structured data processing due to their powerful representation learning capabilities. It is generally believed that GNNs can implicitly remove the non-predictive noises. However, the analysis of implicit denoising effect in graph neural networks remains open. In this work, we conduct a comprehensive theoretical study and analyze when and why the implicit denoising happens in GNNs. Specifically, we study the convergence properties of noise matrix. Our theoretical analysis suggests that the implicit denoising largely depends on the connectivity, the graph size, and GNN architectures. Moreover, we formally define and propose the adversarial graph signal denoising (AGSD) problem by extending graph signal denoising problem. By solving such a problem, we derive a robust graph convolution, where the smoothness of the node representations and the implicit denoising effect can be enhanced. Extensive empirical evaluations verify our theoretical analyses and the effectiveness of our proposed model.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 30 of its 44 references that are in the map. First posted on arXiv 29 Sep 2022.

Builds on

30 of 44 references.

References · 30

  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. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2017Inductive Representation Learning on Large Graphscited by 6,284
  6. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  7. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  9. 2019Simplifying Graph Convolutional Networkscited by 1,470
  10. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  11. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  12. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
18 more
  1. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  2. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  3. 2020Simple and Deep Graph Convolutional Networkscited by 857
  4. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  5. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  6. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
  7. 2021Training Graph Neural Networks with 1000 Layerscited by 169
  8. 2021Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillationcited by 151
  9. 2020A Unified View on Graph Neural Networks as Graph Signal Denoisingcited by 110
  10. 2020Retrosynthesis Prediction with Conditional Graph Logic Networkcited by 103
  11. 2019LanczosNet: Multi-Scale Deep Graph Convolutional Networkscited by 73
  12. 2021Graph Neural Networks Inspired by Classical Iterative Algorithmscited by 60
  13. 2019Certifiable Robustness and Robust Training for Graph Convolutional Networkscited by 59
  14. 2018N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classificationcited by 54
  15. 2019Label Efficient Semi-Supervised Learning via Graph Filteringcited by 46
  16. 2020Graph Unrolling Networks: Interpretable Neural Networks for Graph Signal Denoisingcited by 33
  17. 2021A Unifying Generative Model for Graph Learning Algorithms: Label Propagation, Graph Convolutions, and Combinationscited by 18
  18. 2021Graph Denoising with Framelet Regularizercited by 8

Built on by

Cited by year

Citing papers per year: 2024: 2.

2 papers.

  1. 2024Joint Graph Rewiring and Feature Denoising via Spectral Resonancecited by 11
  2. 2024Graph Adversarial Diffusion Convolutioncited by 0