Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher.
Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?
Some links on this page may take you to non-federal websites. Their policies may differ from this site.
-
Machine learning with missing data has been approached in two different ways, including feature imputation where missing feature values are estimated based on observed values and label prediction where downstream labels are learned directly from incomplete data. However, existing imputation models tend to have strong prior assumptions and cannot learn from downstream tasks, while models targeting label prediction often involve heuristics and can encounter scalability issues. Here we propose GRAPE, a graph-based framework for feature imputation as well as label prediction. GRAPE tackles the missing data problem using a graph representation, where the observations and features are viewed as two types of nodes in a bipartite graph, and the observed feature values as edges. Under the GRAPE framework, the feature imputation is formulated as an edge-level prediction task and the label prediction as a node-level prediction task. These tasks are then solved with Graph Neural Networks. Experimental results on nine benchmark datasets show that GRAPE yields 20% lower mean absolute error for imputation tasks and 10% lower for label prediction tasks, compared with existing state-of-the-art methods.more » « less
-
Detrimental nanoscale gas bubble defects seriously hinder the practical applications of nanoimprint lithography in manufacturing of nanoelectronic devices. Here, we present a nanofluidics study on the formation and evolution mechanisms of nanoscale bubble defects in dispensing-based UV-curable nanoimprint lithography processes. Our work indicates that the formation of nanoscale bubble defects is mainly attributed to the pinning of resist spreading edges at the nanostructures or contaminants on the mold/substrate surfaces. Such pinning-induced nanoscale gas bubbles undergo an evolution process governed by the combinational effect of surface pinning and gas dissolution into resist. Such an evolution process results in a prominent drop of the gas pressure inside bubbles and therefore prevents nanoscale gas bubble defects from the complete dissolution into resists. This work identifies the critical mechanisms responsible for the formation of detrimental nanoscale bubble defects and provides important insights for the ultimate elimination of such defectsmore » « less