mlsanityData to 14 Oct 2026

Robust Graph Neural Networks via Unbiased Aggregation

arXiv 2311.14934 ↗First posted 25 Nov 2023cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

The adversarial robustness of Graph Neural Networks (GNNs) has been questioned due to the false sense of security uncovered by strong adaptive attacks despite the existence of numerous defenses. In this work, we delve into the robustness analysis of representative robust GNNs and provide a unified robust estimation point of view to understand their robustness and limitations. Our novel analysis of estimation bias motivates the design of a robust and unbiased graph signal estimator. We then develop an efficient Quasi-Newton Iterative Reweighted Least Squares algorithm to solve the estimation problem, which is unfolded as robust unbiased aggregation layers in GNNs with theoretical guarantees. Our comprehensive experiments confirm the strong robustness of our proposed model under various scenarios, and the ablation study provides a deep understanding of its advantages. Our code is available at https://github.com/chris-hzc/RUNG.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 24 of its 43 references that are in the map. First posted on arXiv 25 Nov 2023.

Builds on

24 of 43 references.

References · 24

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  4. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  5. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  6. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  7. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
  8. 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
  9. 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
  10. 2022Graph-Coupled Oscillator Networkscited by 124
  11. 2020A Unified View on Graph Neural Networks as Graph Signal Denoisingcited by 110
  12. 2021Robustness of Graph Neural Networks at Scalecited by 100
12 more
  1. 2021TDGIA:Effective Injection Attacks on Graph Neural Networkscited by 67
  2. 2021Elastic Graph Neural Networkscited by 67
  3. 2019Certifiable Robustness to Graph Perturbationscited by 62
  4. 2021Graph Neural Networks Inspired by Classical Iterative Algorithmscited by 60
  5. 2020Reliable Graph Neural Networks via Robust Aggregationcited by 43
  6. 2023Are Defenses for Graph Neural Networks Robust?cited by 38
  7. 2019Batch Virtual Adversarial Training for Graph Convolutional Networkscited by 33
  8. 2022EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networkscited by 26
  9. 2023Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approachcited by 24
  10. 2022GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networkscited by 14
  11. 2019Vector-Valued Graph Trend Filtering with Non-Convex Penaltiescited by 12
  12. 2022Total Variation Graph Neural Networkscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 4.

8 papers.

  1. 2025Boosting Adversarial Robustness and Generalization with Dictionary Structurecited by 1
  2. 2025Robustness in Text-Attributed Graph Learning: Insights, Trade-offs, and New Defensescited by 1
  3. 2024Domain Adaptive Unfolded Graph Neural Networkscited by 0
  4. 2025Adaptive Branch Specialization in Spectral-Spatial Graph Neural Networks for Certified Robustnesscited by 0
  5. 2026Can LLMs Fool Graph Learning? Exploring Universal Adversarial Attacks on Text-Attributed Graphscited by 0
  6. 2026Adversarial Graph Neural Network Benchmarks: Towards Practical and Fair Evaluationcited by 0
  7. 2026GJDNet: Robust Graph Neural Networks via Joint Disentangled Learning Against Adversarial Attackscited by 0
  8. 2026Towards One-for-All Robustness Across a Continuum of Threat Levelscited by 0