One Node One Model: Featuring the Missing-Half for Graph Clustering
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912181256192000 |
|---|---|
| author | Xie, Xuanting Li, Bingheng Pan, Erlin Guo, Zhaochen Kang, Zhao Chen, Wenyu |
| author_facet | Xie, Xuanting Li, Bingheng Pan, Erlin Guo, Zhaochen Kang, Zhao Chen, Wenyu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_09902 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | One Node One Model: Featuring the Missing-Half for Graph Clustering Xie, Xuanting Li, Bingheng Pan, Erlin Guo, Zhaochen Kang, Zhao Chen, Wenyu Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing Social and Information Networks 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. |
| title | One Node One Model: Featuring the Missing-Half for Graph Clustering |
| topic | Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing Social and Information Networks |
| url | https://arxiv.org/abs/2412.09902 |