Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Hui Guan

Toward Compact Parameter Representations for Architecture-Agnostic Neural Network Compression

Nov 19, 2021
Yuezhou Sun, Wenlong Zhao, Lijun Zhang, Xiao Liu, Hui Guan, Matei Zaharia

  Access Paper or Ask Questions

COMET: A Novel Memory-Efficient Deep Learning Training Framework by Using Error-Bounded Lossy Compression

Nov 18, 2021
Sian Jin, Chengming Zhang, Xintong Jiang, Yunhe Feng, Hui Guan, Guanpeng Li, Shuaiwen Leon Song, Dingwen Tao

* 14 pages, 17 figures, accepted by VLDB 2022. arXiv admin note: substantial text overlap with arXiv:2011.09017 

  Access Paper or Ask Questions

AutoMTL: A Programming Framework for Automated Multi-Task Learning

Oct 25, 2021
Lijun Zhang, Xiao Liu, Hui Guan

* 16 pages, 9 figures 

  Access Paper or Ask Questions

Rethinking Hard-Parameter Sharing in Multi-Task Learning

Jul 23, 2021
Lijun Zhang, Qizheng Yang, Xiao Liu, Hui Guan

* 15 pages, 6 figures 

  Access Paper or Ask Questions

Scalable Graph Neural Network Training: The Case for Sampling

May 05, 2021
Marco Serafini, Hui Guan

* 9 pages, 2 figures 

  Access Paper or Ask Questions

SID-NISM: A Self-supervised Low-light Image Enhancement Framework

Dec 16, 2020
Lijun Zhang, Xiao Liu, Erik Learned-Miller, Hui Guan

* 11 pages, 9 figures 

  Access Paper or Ask Questions

Post-Training 4-bit Quantization on Embedding Tables

Nov 05, 2019
Hui Guan, Andrey Malevich, Jiyan Yang, Jongsoo Park, Hector Yuen

* Accepted in [email protected]'19 (

  Access Paper or Ask Questions

In-Place Zero-Space Memory Protection for CNN

Oct 31, 2019
Hui Guan, Lin Ning, Zhen Lin, Xipeng Shen, Huiyang Zhou, Seung-Hwan Lim

* Accepted in NeurIPS'19 

  Access Paper or Ask Questions