Hybrid-Collaborative Augmentation and Contrastive Sample Adaptive-Differential Awareness for Robust Attributed Graph Clustering

An official source code for paper "Hybrid-Collaborative Augmentation and Contrastive Sample Adaptive-Differential Awareness for Robust Attributed Graph Clustering", accepted by NeurIPS 2025. Any communications or issues are welcomed. Please contact zhaotianxiang0474@163.com.
The authors of the paper: Tianxiang Zhao, Youqing Wang, Jinlu Wang, Jiapu Wang, Mingliang Cui, Junbin Gao, Jipeng Guo (Corresponding author).

Overview

We propose a novel Robust Attributed Graph Clustering (RAGC), incorporating Hybrid-Collaborative Augmentation (HCA) and Contrastive Sample Adaptive-Differential Awareness (CSADA). The overall framework of RAGC is illustrated in Fig. 1.

Start

• Step1: unzip the dataset into the ./dataset folder
• Step2: run

python train.py

Citation

If you find this repository helpful, please cite our papers.

@inproceedings{zhao2025hybrid,
  title={Hybrid-Collaborative Augmentation and Contrastive Sample Adaptive-Differential Awareness for Robust Attributed Graph Clustering},
  author={Zhao, Tianxiang and Wang, Youqing and Wang, Jinlu and Wang, Jiapu and Cui, Mingliang and Gao, Junbin and Guo, Jipeng},
  pages={115969--115994},
  booktitle={NeurIPS},
  year={2025}
}