activity
20172023
most citedA Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT

156 citations · 441 across the 39 of their papers we have counts for

collaborators
Showing 2018Show all

5 papers · 1 filter

cs.CL2018

Unsupervised Pseudo-Labeling for Extractive Summarization on Electronic Health Records

Xiangan Liu, Keyang Xu, Pengtao Xie +1

Extractive summarization is very useful for physicians to better manage and digest Electronic Health Records (EHRs). However, the training of a supervised model requires disease-sp…

cs.LG2018

Stackelberg GAN: Towards Provable Minimax Equilibrium via Multi-Generator Architectures

Hongyang Zhang, Susu Xu, Jiantao Jiao +3

We study the problem of alleviating the instability issue in the GAN training procedure via new architecture design. The discrepancy between the minimax and maximin objective value…

cs.LG2018

Multimodal Machine Learning for Automated ICD Coding

Keyang Xu, Mike Lam, Jingzhi Pang +9

This study presents a multimodal machine learning model to predict ICD-10 diagnostic codes. We developed separate machine learning models that can handle data from different modali…

cs.LG2018

Missing Value Imputation Based on Deep Generative Models

Hongbao Zhang, Pengtao Xie, Eric Xing

Missing values widely exist in many real-world datasets, which hinders the performing of advanced data analytics. Properly filling these missing values is crucial but challenging,…

cs.LG2018

Orthogonality-Promoting Distance Metric Learning: Convex Relaxation and Theoretical Analysis

Pengtao Xie, Wei Wu, Yichen Zhu +1

Distance metric learning (DML), which learns a distance metric from labeled "similar" and "dissimilar" data pairs, is widely utilized. Recently, several works investigate orthogona…