Deep Temporal Graph Clustering

• DOI: 10.48550/arxiv.2305.10738
• Publication Date: 2023-01-01
• Authors: Meng Liu; Yue Liu; Ke Liang; Siwei Wang; Sihang Zhou; Xinwang Liu
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Artificial Intelligence (cs.AI); Computer Science - Artificial Intelligence; Machine Learning (cs.LG)

Deep graph clustering has recently received significant attention due to its ability enhance the representation learning capabilities of models in unsupervised scenarios. Nevertheless, deep for temporal graphs, which could capture crucial dynamic interaction information, not been fully explored. It means that many clustering-oriented real-world scenarios, graphs can only be processed as static graphs. This causes loss information but also triggers huge computational consumption. To solve problem, we propose a general framework Temporal Graph Clustering called TGC, introduces techniques suit sequence-based batch-processing pattern In addition, discuss differences between and from several levels. verify superiority proposed conduct extensive experiments. The experimental results show enables more flexibility finding balance time space requirements, our effectively improve performance existing methods. code is released: https://github.com/MGitHubL/Deep-Temporal-Graph-Clustering.