# One Node One Model: Featuring the Missing-Half for Graph Clustering

arXiv: https://arxiv.org/abs/2412.09902 · HTML: https://mlsanity.com/paper/2412.09902/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2024.

## Built on by (most cited first, 7 of 7)

- [Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment](https://mlsanity.com/paper/2502.02017/) (2025)
- [On the Benefits of Attribute-Driven Graph Domain Adaptation](https://mlsanity.com/paper/2502.06808/) (2025)
- [Homophily Enhanced Graph Domain Adaptation](https://mlsanity.com/paper/2505.20089/) (2025)
- [Cooperation of Experts: Fusing Heterogeneous Information with Large Margin](https://mlsanity.com/paper/2505.20853/) (2025)
- [Graph Domain Adaptation via Homophily-Agnostic Reconstructing Structure](https://mlsanity.com/paper/2602.07573/) (2026)
- [Attention Beyond Neighborhoods: Reviving Transformer for Graph Clustering](https://mlsanity.com/paper/2509.15024/) (2025)
- [Selective Hypergraph Refinement for Frozen Graph Clustering](https://mlsanity.com/paper/2609.03265/) (2026)

## Abstract (arXiv)

Most existing graph clustering methods primarily focus on exploiting topological structure, often neglecting the ``missing-half" node feature information, especially how these features can enhance clustering performance. This issue is further compounded by the challenges associated with high-dimensional features. Feature selection in graph clustering is particularly difficult because it requires simultaneously discovering clusters and identifying the relevant features for these clusters. To address this gap, we introduce a novel paradigm called ``one node one model", which builds an exclusive model for each node and defines the node label as a combination of predictions for node groups. Specifically, the proposed ``Feature Personalized Graph Clustering (FPGC)" method identifies cluster-relevant features for each node using a squeeze-and-excitation block, integrating these features into each model to form the final representations. Additionally, the concept of feature cross is developed as a data augmentation technique to learn low-order feature interactions. Extensive experimental results demonstrate that FPGC outperforms state-of-the-art clustering methods. Moreover, the plug-and-play nature of our method provides a versatile solution to enhance GNN-based models from a feature perspective.