Homophily principle,\ie {} nodes with the same labels or similar attributes are more likely to
be connected, has been commonly believed to be the main reason for the superiority of …

Graph Neural Networks (GNNs) have shown promising potential in graph representation
learning. The majority of GNNs define a local message-passing mechanism, propagating …

Composite shear walls have emerged as an innovative and efficient solution for resisting
lateral loads in high-rise buildings. With the inclusion of these types of shear walls in various …

The increasing use of innovative materials in blast-and impact-resistant structures
underscores the demand for robust simulation and design methods. Concrete, especially …

Graph transformers need strong inductive biases to derive meaningful attention scores. Yet,
current methods often fall short in capturing longer ranges, hierarchical structures, or …

Façade cladding system is essential contributor to the sustainable performance of buildings.
Holistic investigation of building facade cladding performance with respect to the regional …

This paper presents a study on the low-velocity impact response of a new steel-
polyurethane foam-steel–concrete-steel (SPUFSCS) panel. The SPUFSCS composite panel …

This study explored the impact responses of a steel–concrete–steel sandwich composite
panel with novel interlocked angle connectors (SCSP-IACs). Impact tests on nine SCSP …

This study conducted a comprehensive examination primarily focused on parametric study
aspects to investigate the integration of smart materials, specifically shear thickening fluids …

Recently, the emerging graph Transformers have made significant advancements for node
classification on graphs. In most graph Transformers, a crucial step involves transforming the …