Introduces an iterative self-learning GNN method for clustering attributed graphs that combines network and attribute information across multiple rounds and outperforms single-round training on synthetic data.
Attributed Graph Clustering via Adaptive Graph Convolution
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Attributed graph clustering is challenging as it requires joint modelling of graph structures and node attributes. Recent progress on graph convolutional networks has proved that graph convolution is effective in combining structural and content information, and several recent methods based on it have achieved promising clustering performance on some real attributed networks. However, there is limited understanding of how graph convolution affects clustering performance and how to properly use it to optimize performance for different graphs. Existing methods essentially use graph convolution of a fixed and low order that only takes into account neighbours within a few hops of each node, which underutilizes node relations and ignores the diversity of graphs. In this paper, we propose an adaptive graph convolution method for attributed graph clustering that exploits high-order graph convolution to capture global cluster structure and adaptively selects the appropriate order for different graphs. We establish the validity of our method by theoretical analysis and extensive experiments on benchmark datasets. Empirical results show that our method compares favourably with state-of-the-art methods.
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Proposes an attention-based contrastive framework fusing multi-scale local topological signals and global cluster prototypes, trained with dual-view losses, reporting competitive results on eight graph datasets.
citing papers explorer
-
Clustering Node Attributed Networks with Graph Neural Networks and Self Learning
Introduces an iterative self-learning GNN method for clustering attributed graphs that combines network and attribute information across multiple rounds and outperforms single-round training on synthetic data.
-
Robust Contrastive Graph Clustering with Adaptive Local-Global Integration
Proposes an attention-based contrastive framework fusing multi-scale local topological signals and global cluster prototypes, trained with dual-view losses, reporting competitive results on eight graph datasets.