# Robust Graph Clustering via Meta Weighting for Noisy Graphs

arXiv: https://arxiv.org/abs/2311.00322 · HTML: https://mlsanity.com/paper/2311.00322/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 61 references that are in the map.
- First posted on arXiv 1 Nov 2023.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Self-Normalizing Neural Networks](https://mlsanity.com/paper/1706.02515/) (2017)
- [Diffusion Improves Graph Learning](https://mlsanity.com/paper/1911.05485/) (2019)
- [Graph Structure Learning for Robust Graph Neural Networks](https://mlsanity.com/paper/2005.10203/) (2020)
- [Graph Representation Learning via Graphical Mutual Information Maximization](https://mlsanity.com/paper/2002.01169/) (2020)
- [GNNGuard: Defending Graph Neural Networks against Adversarial Attacks](https://mlsanity.com/paper/2006.08149/) (2020)
- [Graph Clustering with Graph Neural Networks](https://mlsanity.com/paper/2006.16904/) (2020)
- [Learning to Drop: Robust Graph Neural Network via Topological Denoising](https://mlsanity.com/paper/2011.07057/) (2020)
- [The Rise of Social Bots](https://mlsanity.com/paper/1407.5225/) (2014)
- [Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels](https://mlsanity.com/paper/2201.00232/) (2022)
- [Spam Review Detection with Graph Convolutional Networks](https://mlsanity.com/paper/1908.10679/) (2019)
- [Detection of Novel Social Bots by Ensembles of Specialized Classifiers](https://mlsanity.com/paper/2006.06867/) (2020)
- [Enhanced Doubly Robust Learning for Debiasing Post-click Conversion Rate Estimation](https://mlsanity.com/paper/2105.13623/) (2021)
- [Evaluation of Community Detection Methods](https://mlsanity.com/paper/1807.01130/) (2018)
- [DenseAlert: Incremental Dense-Subtensor Detection in Tensor Streams](https://mlsanity.com/paper/1706.03374/) (2017)
- [Point-of-Interest Recommendation: Exploiting Self-Attentive Autoencoders with Neighbor-Aware Influence](https://mlsanity.com/paper/1809.10770/) (2018)
- [Meta-Learning for Online Update of Recommender Systems](https://mlsanity.com/paper/2203.10354/) (2022)

## Built on by (most cited first, 5 of 5)

- [Tackling Prevalent Conditions in Unsupervised Combinatorial Optimization: Cardinality, Minimum, Covering, and More](https://mlsanity.com/paper/2405.08424/) (2024)
- [Revisiting Dynamic Graph Clustering via Matrix Factorization](https://mlsanity.com/paper/2502.06117/) (2025)
- [Beyond the Academic Monoculture: A Unified Framework and Industrial Perspective for Attributed Graph Clustering](https://mlsanity.com/paper/2603.20829/) (2026)
- [RDSA: A Robust Deep Graph Clustering Framework via Dual Soft Assignment](https://mlsanity.com/paper/2410.21745/) (2024)
- [Weighted Graph Structure Learning with Attention Denoising for Node Classification](https://mlsanity.com/paper/2503.12157/) (2025)

## Abstract (arXiv)

How can we find meaningful clusters in a graph robustly against noise edges? Graph clustering (i.e., dividing nodes into groups of similar ones) is a fundamental problem in graph analysis with applications in various fields. Recent studies have demonstrated that graph neural network (GNN) based approaches yield promising results for graph clustering. However, we observe that their performance degenerates significantly on graphs with noise edges, which are prevalent in practice. In this work, we propose MetaGC for robust GNN-based graph clustering. MetaGC employs a decomposable clustering loss function, which can be rephrased as a sum of losses over node pairs. We add a learnable weight to each node pair, and MetaGC adaptively adjusts the weights of node pairs using meta-weighting so that the weights of meaningful node pairs increase and the weights of less-meaningful ones (e.g., noise edges) decrease. We show empirically that MetaGC learns weights as intended and consequently outperforms the state-of-the-art GNN-based competitors, even when they are equipped with separate denoising schemes, on five real-world graphs under varying levels of noise. Our code and datasets are available at https://github.com/HyeonsooJo/MetaGC.