K-Core based Temporal Graph Convolutional Network for Dynamic Graphs
This work addresses the challenge of dynamic graph embedding for applications requiring evolving graph patterns, representing an incremental improvement over existing methods.
The paper tackles the problem of learning node representations for dynamic graphs, which evolve over time, by proposing a k-core based temporal graph convolutional network (CTGCN) that preserves local and global graph properties while capturing dynamics, and it outperforms state-of-the-art methods on 7 real-world graphs in tasks like link prediction and structural role classification.
Graph representation learning is a fundamental task in various applications that strives to learn low-dimensional embeddings for nodes that can preserve graph topology information. However, many existing methods focus on static graphs while ignoring evolving graph patterns. Inspired by the success of graph convolutional networks(GCNs) in static graph embedding, we propose a novel k-core based temporal graph convolutional network, the CTGCN, to learn node representations for dynamic graphs. In contrast to previous dynamic graph embedding methods, CTGCN can preserve both local connective proximity and global structural similarity while simultaneously capturing graph dynamics. In the proposed framework, the traditional graph convolution is generalized into two phases, feature transformation and feature aggregation, which gives the CTGCN more flexibility and enables the CTGCN to learn connective and structural information under the same framework. Experimental results on 7 real-world graphs demonstrate that the CTGCN outperforms existing state-of-the-art graph embedding methods in several tasks, including link prediction and structural role classification. The source code of this work can be obtained from \url{https://github.com/jhljx/CTGCN}.