Clarify Confused Nodes via Separated Learning.

Graph neural networks (GNNs) have achieved remarkable advances in graph-oriented tasks. However, real-world graphs invariably contain a certain proportion of heterophilous nodes, challenging the homophily assumption of traditional GNNs and hindering their performance. Most existing studies continue to design generic models with shared weights between heterophilous and homophilous nodes.

PathMLP: Smooth path towards high-order homophily.

Real-world graphs exhibit increasing heterophily, where nodes no longer tend to be connected to nodes with the same label, challenging the homophily assumption of classical graph neural networks (GNNs) and impeding their performance. Intriguingly, from the observation of heterophilous data, we notice that certain high-order information exhibits higher homophily, which motivates us to involve high-order information in node representation learning. However, common practices in GNNs to acquire high-order information mainly through increasing model depth and altering message-passing mechanisms, which, albeit effective to a certain extent, suffer from three shortcomings: (1) over-smoothing due to excessive model depth and propagation times; (2) high-order information is not fully utilized; (3) low computational efficiency.

Stiffening of the gluteal muscle increased the intramuscular stress: An in-silico implication of deep tissue injury.

Objectives: Deep tissue injury is a common form of pressure ulcers in muscle tissues under bony prominences caused by sustained pressure or shear, which has a great impact on patients with restricted mobility such as spinal cord injury. Frequent spasms in spinal cord injury patients featured by muscle stiffening may be one of the factors leading to deep tissue injury. The purpose of this study was to investigate the relationship between the gluteal muscle shear modulus and intramuscular compressive/shear stress/strain.