G
Guangxu Xun
Researcher at University of Virginia
Publications - 48
Citations - 1811
Guangxu Xun is an academic researcher from University of Virginia. The author has contributed to research in topics: Context (language use) & Deep learning. The author has an hindex of 17, co-authored 43 publications receiving 1022 citations. Previous affiliations of Guangxu Xun include University at Buffalo.
Papers
More filters
Proceedings ArticleDOI
Identifying inorganic material affinity classes for peptide sequences based on context learning
Guangxu Xun,Xiaoyi Li,Marc R. Knecht,Paras N. Prasad,Mark T. Swihart,Tiffany R. Walsh,Aidong Zhang +6 more
TL;DR: This paper proposes a novel framework to identify affinity classes for peptide sequences across inorganic materials by analyzing the structure and affinity class of each peptide sequence and training a classifier based on these vector features and the heuristic rules.
Journal ArticleDOI
FAT-RE: A faster dependency-free model for relation extraction
TL;DR: A faster dependency-free model is proposed, regarding the sentence as a fully-connected graph, and customize the vanilla transformer architecture to remove the irrelevant information via filtering mechanism and further aggregate the sentence information through the enhanced query.
Proceedings ArticleDOI
GLIMA: Global and Local Time Series Imputation with Multi-directional Attention Learning
TL;DR: In this paper, the authors propose an imputation framework to learn both global and local dependencies of multivariate time series, as well as a multi-dimensional self-attention to learn capture distant correlations across both time and feature.
Proceedings ArticleDOI
A Stagewise Hyperparameter Scheduler to Improve Generalization
TL;DR: In this paper, a general formulation of quasi-hyperbolic momentum (QHM) is used to tune a large class of momentum variants to improve generalization, including heavy ball momentum and Nesterov's accelerated gradient.