Dynamic Graph Echo State Networks
This work addresses the challenge of efficiently modeling evolving relations in domains like social networks or infection spreading, but it is incremental as it builds on existing graph echo state networks.
The authors tackled the problem of processing dynamic temporal graphs, such as social network interactions, by proposing an extension of graph echo state networks that provides efficient vector encodings updated at each time-step without training, achieving accuracy comparable to approximate temporal graph kernels on twelve dissemination process classification tasks.
Dynamic temporal graphs represent evolving relations between entities, e.g. interactions between social network users or infection spreading. We propose an extension of graph echo state networks for the efficient processing of dynamic temporal graphs, with a sufficient condition for their echo state property, and an experimental analysis of reservoir layout impact. Compared to temporal graph kernels that need to hold the entire history of vertex interactions, our model provides a vector encoding for the dynamic graph that is updated at each time-step without requiring training. Experiments show accuracy comparable to approximate temporal graph kernels on twelve dissemination process classification tasks.