Multiview Temporal Graph Clustering

• Published in: IEEE transaction on neural networks and learning systems Vol. PP; pp. 1 - 14
• Main Authors: Liu, Meng, Liang, Ke, Yu, Hao, Meng, Lingyuan, Wang, Siwei, Zhou, Sihang, Liu, Xinwang
• Format: Journal Article
• Language: English
• Published: United States IEEE 15.07.2025
• Subjects: Clustering methods; Data models; Focusing; Graph learning; Heavily-tailed distribution; Learning systems; Matrix decomposition; multiview clustering (MVC); Noise measurement; Reliability; Sparse matrices; temporal graph clustering (TGC); Training
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2025.3584384

As an emerging task, temporal graph clustering (TGC) is committed to clustering nodes on temporal graphs through interaction sequence-based batch-processing patterns. These patterns allow for more flexibility in finding a balance between time and space requirements than adjacency matrix-based static graph clustering. However, as a new task, TGC still has important unresolved challenges, such as insufficient information. This challenge manifests itself in a variety of problems in real-world datasets, including missing features (eigenvalues are missing or even nonexistent), long-tail nodes (most inactive nodes have little interaction), and noisy data (data is subject to anomalies, errors, and sparsity). These problems occur before training, making it difficult for the model to train well with insufficient information. To solve the challenge, we propose a method that introduces multiview clustering (MVC) into TGC, called MVTGC. Our method aims to perform data augmentation on the temporal graph by constructing multiple views to increase the information richness. In particular, we utilize different techniques to model a certain part of the temporal graph to generate enhanced views focusing on different angles. These views are combined into training through early fusion and late fusion and ultimately enhance the model's receptive field and information richness. Comparative experiments and a case study on real-world datasets demonstrate the significance and effectiveness of MVTGC, which achieves at most 10.48% performance improvement. The code and data are available at https://github.com/MGitHubL/MVTGC