tl;dr: We provably improve GNN expressivity by enhancing message passing with substructure encodings. Our method allows incorporating domain specific prior knowledge and can be used as a drop-in ...

Creative Commons (CC): This is a Creative Commons license. Attribution (BY): Credit must be given to the creator. The processing of chemical information by computational intelligence methods faces the ...

To effectively evaluate a system that performs operations on UML class diagrams, it is essential to cover a large variety of different types of diagrams. The coverage of the diagram space can be ...

Creative Commons (CC): This is a Creative Commons license. Attribution (BY): Credit must be given to the creator. Accurately modeling chemical reactions in molecular dynamics simulations requires ...

Abstract: Conventional intent-driven networks (IDNs) rely on static templates to translate declarative intents into imperative network configurations. However, the dynamic nature of network ...

Metallic alloys underpin many technological advancements. In these materials two or more chemical elements are mixed together, often forming phases in which elements are spread out in an almost random ...

Control flow graphs (CFGs) generated through a dynamic or emulated approach contain many benefits over statically generated CFGs such as yielding smaller, more well connected, and less noisy graphs.

In this potentially useful study, the authors employ concepts and algorithms associated with induced subgraph in graph theory to automate several key but non-trivial steps in the development of coarse ...

The authors present an important multi-scale computational platform, which aims to automate the workflow for coarse-grained simulations of biomolecules in the framework of the popular MARTINI model.