Constrained by the limitations of learning toolkits engineered for other applications, such as
those in image processing, many mesh-based learning algorithms employ data flows that …

A fundamental task in data exploration is to extract low dimensional representations that
capture intrinsic geometry in data, especially for faithfully visualizing data in two or three …

In real-world machine learning applications, unlabeled training data are readily available,
but labeled data are expensive and hard to obtain. Therefore, semi-supervised learning …

High-resolution and high-efficiency simulations are a great challenge in a material extrusion
process. This paper developed a reduced-order thermo-viscoelastic model based on …

Label noise is prevalent in real-world visual learning applications and correcting all label
mistakes can be prohibitively costly. Training neural network classifiers on such noisy …

This paper presents a mixed Graph-FEM (Finite Element Method) approach for the phase
field modeling of fracture in plates and shells composed of nonlinearly elastic solids. In this …

Part-level thermal-mechanical simulation with filament resolution is currently a significant
challenge for material extrusion processes. This paper proposed a novel method to achieve …

Nearest neighbour graphs are widely used to capture the geometry or topology of a dataset.
One of the most common strategies to construct such a graph is based on selecting a fixed …

The high dimensionality of modern data introduces significant challenges in descriptive and
exploratory data analysis. These challenges gave rise to extensive work on dimensionality …