Christopher Morris

TL;DR: It is confirmed that taking temporal information into account is crucial for the successful classification of dissemination processes and three different approaches are explored and the trade-offs between loss of temporal information and efficiency are investigated.

TL;DR: In this paper , the authors investigate the limitations in the expressive power of the well-known Relational GCN and Compositional GCN architectures and shed some light on their practical learning performance, and establish under which conditions both models have the same expressive power in distinguishing non-isomorphic (multi-relational) graphs or vertices with different structural roles.

TL;DR: This work introduces a framework to lift standard graph kernels and graph-based neural networks to the temporal domain and shows that its methods beat static approaches by a large margin in terms of accuracy while still being scalable to large graphs and data sets.

TL;DR: Mueller et al. as mentioned in this paper presented a taxonomy of graph transformer architectures, including structural and positional encodings, and discussed extensions for important graph classes, e.g., 3D molecular graphs.

TL;DR: The ML4CO aims at improving state-of-the-art combinatorial optimization solvers by replacing key heuristic components by giving an appropriate solver configuration.