# Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN

arXiv: https://arxiv.org/abs/2207.00012 · HTML: https://mlsanity.com/paper/2207.00012/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 60 references that are in the map.
- First posted on arXiv 30 Jun 2022.

## Builds on (most cited first, 30 of 40)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Contrastive Multi-View Representation Learning on Graphs](https://mlsanity.com/paper/2006.05582/) (2020)
- [Adaptive Universal Generalized PageRank Graph Neural Network](https://mlsanity.com/paper/2006.07988/) (2020)
- [Deep Graph Contrastive Representation Learning](https://mlsanity.com/paper/2006.04131/) (2020)
- [MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing](https://mlsanity.com/paper/1905.00067/) (2019)
- [InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization](https://mlsanity.com/paper/1908.01000/) (2019)
- [Adversarial Attacks on Neural Networks for Graph Data](https://mlsanity.com/paper/1805.07984/) (2018)
- [Deep Learning on Graphs: A Survey](https://mlsanity.com/paper/1812.04202/) (2018)
- [Graph Structure Learning for Robust Graph Neural Networks](https://mlsanity.com/paper/2005.10203/) (2020)
- [Adversarial Attack on Graph Structured Data](https://mlsanity.com/paper/1806.02371/) (2018)
- [Adversarial Attacks on Graph Neural Networks via Meta Learning](https://mlsanity.com/paper/1902.08412/) (2019)
- [Graph Representation Learning via Graphical Mutual Information Maximization](https://mlsanity.com/paper/2002.01169/) (2020)
- [Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings](https://mlsanity.com/paper/2006.13009/) (2020)
- [Data Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2006.06830/) (2020)
- [Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective](https://mlsanity.com/paper/1906.04214/) (2019)
- [GNNGuard: Defending Graph Neural Networks against Adversarial Attacks](https://mlsanity.com/paper/2006.08149/) (2020)
- [A Fine-Grained Analysis on Distribution Shift](https://mlsanity.com/paper/2110.11328/) (2021)
- [Adaptive Graph Convolutional Neural Networks](https://mlsanity.com/paper/1801.03226/) (2018)
- [Learning to Drop: Robust Graph Neural Network via Topological Denoising](https://mlsanity.com/paper/2011.07057/) (2020)
- [AM-GCN: Adaptive Multi-channel Graph Convolutional Networks](https://mlsanity.com/paper/2007.02265/) (2020)

## Built on by (most cited first, 30 of 34)

- [GSLB: The Graph Structure Learning Benchmark](https://mlsanity.com/paper/2310.05174/) (2023)
- [SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization](https://mlsanity.com/paper/2303.09778/) (2023)
- [GraphEdit: Large Language Models for Graph Structure Learning](https://mlsanity.com/paper/2402.15183/) (2024)
- [OpenGSL: A Comprehensive Benchmark for Graph Structure Learning](https://mlsanity.com/paper/2306.10280/) (2023)
- [Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach](https://mlsanity.com/paper/2310.06396/) (2023)
- [Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?](https://mlsanity.com/paper/2408.08685/) (2024)
- [DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing](https://mlsanity.com/paper/2401.12780/) (2024)
- [A Unified Framework of Graph Information Bottleneck for Robustness and Membership Privacy](https://mlsanity.com/paper/2306.08604/) (2023)
- [Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning](https://mlsanity.com/paper/2409.17386/) (2024)
- [Data Augmentation on Graphs: A Technical Survey](https://mlsanity.com/paper/2212.09970/) (2022)
- [A clean-label graph backdoor attack method in node classification task](https://mlsanity.com/paper/2401.00163/) (2023)
- [Self-Guided Robust Graph Structure Refinement](https://mlsanity.com/paper/2402.11837/) (2024)
- [RobGC: Towards Robust Graph Condensation](https://mlsanity.com/paper/2406.13200/) (2024)
- [FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification](https://mlsanity.com/paper/2210.13815/) (2022)
- [Minimum Topology Attacks for Graph Neural Networks](https://mlsanity.com/paper/2403.02723/) (2024)
- [Cooperation of Experts: Fusing Heterogeneous Information with Large Margin](https://mlsanity.com/paper/2505.20853/) (2025)
- [IDEA: Invariant Defense for Graph Adversarial Robustness](https://mlsanity.com/paper/2305.15792/) (2023)
- [Bridging Large Language Models and Graph Structure Learning Models for Robust Representation Learning](https://mlsanity.com/paper/2410.12096/) (2024)
- [Prompt-based Unifying Inference Attack on Graph Neural Networks](https://mlsanity.com/paper/2412.15735/) (2024)
- [Graph Structure Refinement with Energy-based Contrastive Learning](https://mlsanity.com/paper/2412.17856/) (2024)
- [Graph Defense Diffusion Model](https://mlsanity.com/paper/2501.11568/) (2025)
- [Graph Agent Network: Empowering Nodes with Inference Capabilities for Adversarial Resilience](https://mlsanity.com/paper/2306.06909/) (2023)
- [Towards Inductive Robustness: Distilling and Fostering Wave-induced Resonance in Transductive GCNs Against Graph Adversarial Attacks](https://mlsanity.com/paper/2312.08651/) (2023)
- [Sparse but Strong: Crafting Adversarially Robust Graph Lottery Tickets](https://mlsanity.com/paper/2312.06568/) (2023)
- [Motif-driven Subgraph Structure Learning for Graph Classification](https://mlsanity.com/paper/2406.08897/) (2024)
- [Robustness in Text-Attributed Graph Learning: Insights, Trade-offs, and New Defenses](https://mlsanity.com/paper/2510.17185/) (2025)
- [DEGNN: Dual Experts Graph Neural Network Handling Both Edge and Node Feature Noise](https://mlsanity.com/paper/2404.09207/) (2024)
- [Graph Adversarial Diffusion Convolution](https://mlsanity.com/paper/2406.02059/) (2024)
- [SFR-GNN: Simple and Fast Robust GNNs against Structural Attacks](https://mlsanity.com/paper/2408.16537/) (2024)
- [Training Robust Graph Neural Networks by Modeling Noise Dependencies](https://mlsanity.com/paper/2502.19670/) (2025)

## Abstract (arXiv)

Benefiting from the message passing mechanism, Graph Neural Networks (GNNs) have been successful on flourish tasks over graph data. However, recent studies have shown that attackers can catastrophically degrade the performance of GNNs by maliciously modifying the graph structure. A straightforward solution to remedy this issue is to model the edge weights by learning a metric function between pairwise representations of two end nodes, which attempts to assign low weights to adversarial edges. The existing methods use either raw features or representations learned by supervised GNNs to model the edge weights. However, both strategies are faced with some immediate problems: raw features cannot represent various properties of nodes (e.g., structure information), and representations learned by supervised GNN may suffer from the poor performance of the classifier on the poisoned graph. We need representations that carry both feature information and as mush correct structure information as possible and are insensitive to structural perturbations. To this end, we propose an unsupervised pipeline, named STABLE, to optimize the graph structure. Finally, we input the well-refined graph into a downstream classifier. For this part, we design an advanced GCN that significantly enhances the robustness of vanilla GCN without increasing the time complexity. Extensive experiments on four real-world graph benchmarks demonstrate that STABLE outperforms the state-of-the-art methods and successfully defends against various attacks.