Pengtao Xie

Publications
Influence

COVID-CT-Dataset: A CT Scan Dataset about COVID-19

Xingyi Yang, J. Zhao, Yichen Zhang, Xuehai He, Pengtao Xie
Computer Science, Engineering
ArXiv
30 March 2020

We build a publicly available CT scan dataset about COVID-19, to foster the development of AI methods for using CT to screen and test CO VID-19 based on CT. Expand

Petuum: A New Platform for Distributed Machine Learning on Big Data

E. Xing, Q. Ho, +7 authors Y. Yu
Computer Science
IEEE Transactions on Big Data
30 December 2013

We propose a general-purpose framework, Petuum, that systematically addresses data- and model-parallel challenges in large-scale ML, by observing that many ML programs are fundamentally optimization-centric and admit error-tolerant, iterative-convergent algorithmic solutions. Expand

Poseidon: An Efficient Communication Architecture for Distributed Deep Learning on GPU Clusters

H. Zhang, Zeyu Zheng, +7 authors E. Xing
Computer Science, Mathematics
USENIX Annual Technical Conference
11 June 2017

We present Poseidon, an efficient communication architecture for distributed DL on GPUs. Expand

On the Automatic Generation of Medical Imaging Reports

Baoyu Jing, Pengtao Xie, E. Xing
Computer Science
ACL
22 November 2017

We propose a co-attention mechanism to localize regions containing abnormalities and generate narrations for them, and develop a hierarchical LSTM model to generate long paragraphs. Expand

Petuum: A New Platform for Distributed Machine Learning on Big Data

E. Xing, Q. Ho, +7 authors Y. Yu
Computer Science
IEEE Trans. Big Data
1 June 2015

Integrating Document Clustering and Topic Modeling

Pengtao Xie, E. Xing
Computer Science, Mathematics
UAI
11 August 2013

We propose a multi-grain clustering topic model (MGCTM) which integrates document clustering and topic modeling into a unified framework and jointly performs the two tasks to achieve the overall best performance. Expand

Towards Automated ICD Coding Using Deep Learning

Haoran Shi, Pengtao Xie, Zhiting Hu, M. Zhang, E. Xing
Computer Science
ArXiv
11 November 2017

We use character-aware neural language models to generate hidden representations of written diagnosis descriptions and ICD codes, and design an attention mechanism to address the mismatch between the numbers of descriptions and corresponding codes. Expand

Incorporating Word Correlation Knowledge into Topic Modeling

Pengtao Xie, Diyi Yang, E. Xing
Computer Science
HLT-NAACL
2015

We build a Markov Random Field (MRF) regularized Latent Dirichlet Allocation (LDA) model, which defines a MRF on the latent topic layer of LDA to encourage words labeled as similar to share the same topic label. Expand

Crypto-Nets: Neural Networks over Encrypted Data

Pengtao Xie, M. Bilenko, T. Finley, Ran Gilad-Bachrach, Kristin E. Lauter, M. Naehrig
Computer Science
ArXiv
18 December 2014

We use homomorphic encryption in the following protocol: the data owner encrypts the data and sends the ciphertexts to the third party to obtain a prediction from a trained model. Expand

Diversifying Restricted Boltzmann Machine for Document Modeling

Pengtao Xie, Y. Deng, E. Xing
Computer Science, Mathematics
KDD
10 August 2015

We propose Diversified RBM which diversifies the hidden units, to make them cover not only the dominant topics, but also those in the long-tail region. Expand

Recommended Authors