P
Pang-Ning Tan
Researcher at Michigan State University
Publications - 200
Citations - 13333
Pang-Ning Tan is an academic researcher from Michigan State University. The author has contributed to research in topics: Cluster analysis & Association rule learning. The author has an hindex of 43, co-authored 191 publications receiving 11436 citations. Previous affiliations of Pang-Ning Tan include University of Minnesota & United States Department of the Army.
Papers
More filters
Proceedings ArticleDOI
Support envelopes: a technique for exploring the structure of association patterns
TL;DR: This paper introduces support envelopes---a new tool for analyzing association patterns---and illustrates some of their properties, applications, and possible extensions.
Journal ArticleDOI
A framework for joint community detection across multiple related networks
TL;DR: This paper presents a framework that identifies communities simultaneously across different networks and learns the correspondences between them, applicable to networks generated from multiple web sites as well as to those derived from heterogeneous nodes of the same web site.
Proceedings ArticleDOI
A Low Rank Weighted Graph Convolutional Approach to Weather Prediction
TL;DR: A novel deep learning approach based on a coupled weighted graph convolutional LSTM (WGC-LSTM), which outperforms all other baseline methods for the majority of the evaluated locations and introduces an additional O(|V|^2) parameters to be estimated, where V is the number of locations.
Journal ArticleDOI
Macroscale patterns of synchrony identify complex relationships among spatial and temporal ecosystem drivers
Noah R. Lottig,Pang-Ning Tan,Tyler Wagner,Kendra Spence Cheruvelil,Patricia A. Soranno,Emily H. Stanley,Caren E. Scott,Craig A. Stow,Shuai Yuan +8 more
TL;DR: In this article, the authors used pattern analysis algorithms and data spanning 22-25-yr from 601 lakes to ask three questions: What are the temporal patterns of lake water clarity at sub-continental scales.
Proceedings Article
FORMULA: FactORized MUlti-task LeArning for task discovery in personalized medical models
TL;DR: A novel approach called FactORized MUlti-task LeArning model (Formula), which learns the personalized model of each patient via a sparse multi-task learning method, which delivered superior predictive performance while the personalized models offered many useful medical insights.