N
Nitesh V. Chawla
Researcher at University of Notre Dame
Publications - 434
Citations - 52969
Nitesh V. Chawla is an academic researcher from University of Notre Dame. The author has contributed to research in topics: Computer science & Health care. The author has an hindex of 61, co-authored 388 publications receiving 41365 citations. Previous affiliations of Nitesh V. Chawla include University of South Florida & Wrocław University of Technology.
Papers
More filters
Book ChapterDOI
An Optimized NL2SQL System for Enterprise Data Mart
TL;DR: The NL2SQL system as mentioned in this paper is designed for the banking sector, which can generate a SQL query from a user's natural language question, based on WikiSQL data, which is extended to support multitable scenarios via a unique table expand process.
Journal ArticleDOI
Knowledge Distillation on Graphs: A Survey
TL;DR: Recently, knowledge distillation on graphs (KDGNNs) as discussed by the authors has attracted tremendous attention by demonstrating their capability to handle graph data and has been introduced to build a smaller yet effective model and exploit more knowledge from data.
Proceedings ArticleDOI
Hierarchical Spatio-Temporal Graph Neural Networks for Pandemic Forecasting
TL;DR: HiSTGNN is proposed, which learns both spatial and temporal information from a sequence of dynamic mobility graphs, and is superior predictive power of COVID-19 new case/death counts compared with state-of-the-art baselines.
Proceedings ArticleDOI
ImWalkMF: Joint matrix factorization and implicit walk integrative learning for recommendation
TL;DR: A joint model of matrix factorization and implicit walk integrative learning, i.e., ImWalkMF, which only uses explicit ratings information yet models both direct rating feedbacks and multiple direct/indirect implicit correlations among users and items from a random walk perspective is designed.
Journal ArticleDOI
Efficient Augmentation for Imbalanced Deep Learning
TL;DR: Expansive Over- Sampling (EOS) is proposed as a data augmentation technique to utilize in the training framework for imbalanced data, showing that effective augmentation via oversampling does not require generative models and should be connected with a deep learning model.