Meng Liu, Yue Liu, Ke Liang, Siwei Wang, Sihang Zhou...
TL;DR提出了基于交互序列的批处理模式的 deep Temporal Graph Clustering (TGC) 框架,通过调整聚类分配和邻接矩阵重建技术来适应时间图的互动动态。实验结果表明,TGC 框架可以有效提高现有临时图学习方法的性能。
Abstract
deep graph clustering has recently received significant attention due to its
ability to enhance the representation learning capabilities of models in
unsupervised scenarios. Nevertheless, deep clustering for temporal gr