Filtration Surfaces for Dynamic Graph Classification
This addresses scalability and flexibility issues in dynamic graph classification for applications where edge weights are important, representing an incremental improvement over existing methods.
The paper tackles the problem of dynamic graph classification by proposing filtration surfaces, a scalable and flexible method that outperforms previous state-of-the-art baselines on datasets relying on edge weight information, with results showing the lowest overall standard deviation among similarly scalable methods.
Existing approaches for classifying dynamic graphs either lift graph kernels to the temporal domain, or use graph neural networks (GNNs). However, current baselines have scalability issues, cannot handle a changing node set, or do not take edge weight information into account. We propose filtration surfaces, a novel method that is scalable and flexible, to alleviate said restrictions. We experimentally validate the efficacy of our model and show that filtration surfaces outperform previous state-of-the-art baselines on datasets that rely on edge weight information. Our method does so while being either completely parameter-free or having at most one parameter, and yielding the lowest overall standard deviation among similarly scalable methods.