Y
Yuqiang Chen
Researcher at Paradigm
Publications - 7
Citations - 369
Yuqiang Chen is an academic researcher from Paradigm. The author has contributed to research in topics: Field (computer science) & Artificial neural network. The author has an hindex of 4, co-authored 7 publications receiving 264 citations.
Papers
More filters
Proceedings ArticleDOI
The Simpler The Better: A Unified Approach to Predicting Original Taxi Demands based on Large-Scale Online Platforms
TL;DR: This work proposes LinUOTD, a unified linear regression model with more than 200 million dimensions of features, which outperforms popular non-linear models in accuracy and can shed insights upon other industrial large-scale spatio-temporal prediction problems.
Proceedings ArticleDOI
AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications
Luo Yuanfei,Mengshuo Wang,Hao Zhou,Quanming Yao,Wei-Wei Tu,Yuqiang Chen,Wenyuan Dai,Qiang Yang +7 more
TL;DR: In this paper, an automatic feature crossing tool provided by 4Paradigm to its customers, ranging from banks, hospitals, to Internet corporations, enables efficient generation of high-order cross features, which is not yet visited by existing works.
Proceedings ArticleDOI
Network On Network for Tabular Data Classification in Real-world Applications
TL;DR: Extensive experiments on six real-world datasets demonstrate Network On Network can outperform the state-of-the-art models significantly and both qualitative and quantitative study of the features in the embedding space show NON can capture intra-field information effectively.
Book ChapterDOI
AutoML @ NeurIPS 2018 Challenge: Design and Results
Hugo Jair Escalante,Wei-Wei Tu,Isabelle Guyon,Daniel Silver,Daniel Silver,Evelyne Viegas,Yuqiang Chen,Wenyuan Dai,Qiang Yang +8 more
TL;DR: A data driven competition asked participants to develop computer programs capable of solving supervised learning problems where the i.i.d. assumption did not hold and CodaLab was used as the challenge platform.
Journal ArticleDOI
Optimizing in-memory database engine for AI-powered on-line decision augmentation using persistent memory
Cheng Chen,Yang Jun,Lu Mian,Taize Wang,Zhao Zheng,Yuqiang Chen,Wenyuan Dai,Bingsheng He,Weng-Fai Wong,Guoan Wu,Yuping Zhao,Andy Rudoff +11 more
TL;DR: Experimental results show that FEDB can be one to two orders of magnitude faster than the state-of-the-art in-memory databases on real-time feature extraction, and the use of the Intel Optane DC Persistent Memory Module (PMEM) is explored to make FEDBs more cost-effective.