Dynamics Based Features For Graph Classification
This addresses the problem of classifying complex networks in fields like social and medical sciences, offering an incremental improvement over existing methods.
The authors tackled graph classification by proposing dynamics-based features derived from generalized assortativities across multiple time scales, achieving competitive and often state-of-the-art accuracies on established benchmarks and a new human brain network dataset.
Numerous social, medical, engineering and biological challenges can be framed as graph-based learning tasks. Here, we propose a new feature based approach to network classification. We show how dynamics on a network can be useful to reveal patterns about the organization of the components of the underlying graph where the process takes place. We define generalized assortativities on networks and use them as generalized features across multiple time scales. These features turn out to be suitable signatures for discriminating between different classes of networks. Our method is evaluated empirically on established network benchmarks. We also introduce a new dataset of human brain networks (connectomes) and use it to evaluate our method. Results reveal that our dynamics based features are competitive and often outperform state of the art accuracies.