# Attributed Graph Clustering with Multi-Scale Weight-Based Pairwise Coarsening and Contrastive Learning

arXiv: https://arxiv.org/abs/2507.20505 · HTML: https://mlsanity.com/paper/2507.20505/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 53 references that are in the map.
- First posted on arXiv 28 Jul 2025.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Contrastive Clustering](https://mlsanity.com/paper/2009.09687/) (2020)
- [Attributed Graph Clustering: A Deep Attentional Embedding Approach](https://mlsanity.com/paper/1906.06532/) (2019)
- [Attributed Graph Clustering via Adaptive Graph Convolution](https://mlsanity.com/paper/1906.01210/) (2019)
- [Scaling Up Graph Neural Networks Via Graph Coarsening](https://mlsanity.com/paper/2106.05150/) (2021)
- [Deep Fusion Clustering Network](https://mlsanity.com/paper/2012.09600/) (2020)
- [CONVERT:Contrastive Graph Clustering with Reliable Augmentation](https://mlsanity.com/paper/2308.08963/) (2023)
- [ResNorm: Tackling Long-tailed Degree Distribution Issue in Graph Neural Networks via Normalization](https://mlsanity.com/paper/2206.08181/) (2022)
- [SCGC : Self-Supervised Contrastive Graph Clustering](https://mlsanity.com/paper/2204.12656/) (2022)
- [CaEGCN: Cross-Attention Fusion based Enhanced Graph Convolutional Network for Clustering](https://mlsanity.com/paper/2101.06883/) (2021)
- [Hierarchical graph neural nets can capture long-range interactions](https://mlsanity.com/paper/2107.07432/) (2021)
- [Graph-based data clustering via multiscale community detection](https://mlsanity.com/paper/1909.04491/) (2019)
- [NCAGC: A Neighborhood Contrast Framework for Attributed Graph Clustering](https://mlsanity.com/paper/2206.07897/) (2022)
- [Features Based Adaptive Augmentation for Graph Contrastive Learning](https://mlsanity.com/paper/2207.01792/) (2022)
- [A Multiscale Graph Convolutional Network Using Hierarchical Clustering](https://mlsanity.com/paper/2006.12542/) (2020)
- [Tree-based Coarsening and Partitioning of Complex Networks](https://mlsanity.com/paper/1402.2782/) (2014)
- [Regularization and Optimization in Model-Based Clustering](https://mlsanity.com/paper/2302.02450/) (2023)

## Abstract (arXiv)

This study introduces the Multi-Scale Weight-Based Pairwise Coarsening and Contrastive Learning (MPCCL) model, a novel approach for attributed graph clustering that effectively bridges critical gaps in existing methods, including long-range dependency, feature collapse, and information loss. Traditional methods often struggle to capture high-order graph features due to their reliance on low-order attribute information, while contrastive learning techniques face limitations in feature diversity by overemphasizing local neighborhood structures. Similarly, conventional graph coarsening methods, though reducing graph scale, frequently lose fine-grained structural details. MPCCL addresses these challenges through an innovative multi-scale coarsening strategy, which progressively condenses the graph while prioritizing the merging of key edges based on global node similarity to preserve essential structural information. It further introduces a one-to-many contrastive learning paradigm, integrating node embeddings with augmented graph views and cluster centroids to enhance feature diversity, while mitigating feature masking issues caused by the accumulation of high-frequency node weights during multi-scale coarsening. By incorporating a graph reconstruction loss and KL divergence into its self-supervised learning framework, MPCCL ensures cross-scale consistency of node representations. Experimental evaluations reveal that MPCCL achieves a significant improvement in clustering performance, including a remarkable 15.24% increase in NMI on the ACM dataset and notable robust gains on smaller-scale datasets such as Citeseer, Cora and DBLP.