Dynamic GraphConvolutional Network (DyGCN) generalizes the embedding propagation scheme of GCN to dynamicsetting in an efficient manner . The most affected nodes are first updated, and then their changes are propagated to the further nodes and leads to theirupdate . Extensive experiments conducted on various dynamic graphs demonstratethat our model can update the node embeddings in a time-saving andperformance-preserving way . We propose an efficient dynamic graph embedding approach, DyGCN, which is an extension of the GCN-based methods . We hope to use this approach to learn low-dimensional representations (aka.embeddings) of nodes .

Author(s) : Zeyu Cui, Zekun Li, Shu Wu, Xiaoyu Zhang, Qiang Liu, Liang Wang, Mengmeng Ai

Links : PDF - Abstract

Code :

Keywords : dynamic - dygcn - embedding - graph - nodes -

Leave a Reply

Your email address will not be published. Required fields are marked *