Deep graph clustering improved by compactness and consistency framework
Compactness and Consistency: A Conjoint Framework for Deep Graph Clustering
Machine LearningArtificial IntelligenceInformation RetrievalSocial and Information Networks
Summary
Graph clustering groups together similar points in a network, but existing methods struggle to capture big-picture connections and often produce unclear groupings due to noisy data. The authors propose a new framework called CoCo that learns clearer, more compact node representations by combining local and global views of the graph and ensuring the information is consistent across these views. This approach helps reduce noise and discover the true underlying structure of the data. Their tests show CoCo performs better than previous methods on multiple datasets.
What this means in practice
- •For social network analysts: Identify more meaningful communities in social graphs by extracting clearer and compact representations from noisy social data.
- •For biomedical data teams: Improve grouping of related biological entities like proteins or cells by better handling noisy and redundant network data.
Authors
Wei Ju, Siyu Yi, Kangjie Zheng, Yifan Wang, Ziyue Qiao, Li Shen, Yongdao Zhou, Xiaochun Cao, Jiancheng Lv
Abstract
Graph clustering is a fundamental task in data analysis, aiming at grouping nodes with similar characteristics in the graph into clusters. This problem has been widely explored using graph neural networks (GNNs) due to their ability to leverage node attributes and graph topology for effective cluster assignments. However, representations learned through GNNs typically struggle to capture global relationships between nodes via local message-passing mechanisms. Moreover, the redundancy and noise inherently present in graph data may easily result in node representations lacking compactness and robustness. To address these issues, we propose a conjoint framework CoCo, which captures compactness and consistency in the learned node representations for deep graph clustering. Technically, our CoCo leverages graph convolutional filters to learn robust node representations from both local and global views, and then encodes them into low-rank compact embeddings, thus effectively removing the redundancy and noise as well as uncovering the intrinsic underlying structure. To further enrich the node semantics, we develop a consistency learning strategy based on compact embeddings to facilitate knowledge transfer from the two perspectives. Our experimental results indicate that our CoCo outperforms state-of-the-art counterparts on various datasets.