I am currently a first-year PhD student of Computer Science and Engineering at The Intelligent Data Analytics (ILLIDAN) Lab
@Michigan State University, advised by Prof. Jiayu Zhou.
I received my Computer Science master degree from University of Southern California (USC) in 2020,
and the Bachelor's Degree from School of Computer Science and Engineering, University of Electronic
Science and Technology of China (UESTC) in 2018.
During 2021-2022, I worked as research assistant, advised by Prof. Zenglin
Xu and Prof. Irwin King.
My research interests include federated learning,
open-source software development. Our open-source tensor decomposition
library TensorD
has 82 stars.
And our federated learning framework FedLab has 400 stars already. I am also working
on benchmark for Federated Learning with Noisy Label, called FedNoisy, to help researchers to have standardized and comparable experiment settings.
Here is my project list for USC CSCI-571, and hope you
have fun. Some links may be outdate.
Frameworks: PyTorch, FedLab, TensorFlow, Apache Spark, Angular, Android, MXNet
Cloud Computing Service: Microsoft Azure, Google Cloud Platform
-
Siqi Liang, Jintao Huang, Junyuan Hong, Dun Zeng, Jiayu Zhou, Zenglin Xu
FedNoisy: Federated Noisy Label Learning Benchmark
arXiv preprint arXiv:2306.11650, 2023. [Code] -
Dun Zeng*, Siqi Liang*, Xiangjin Hu, Zenglin Xu (* equal contribution in random order)
FedLab: A Flexible Federated Learning Framework
The Journal of Machine Learning Research, 24(100):1−7, 2023. [Code] [Benchmark] -
Andrew B Chen, Siqi Liang, Jessica H Nguyen, Yan Liu, Andrew J Hung
Machine learning analyses of automated performance metrics during granular sub-stitch phases predict surgeon experience
Surgery, 2021. -
Benjamin Y Xu, Siqi Liang, Anmol A Pardeshi, Jacob Lifton, Sasan Moghimi, Juan Pablo Lewinger, Rohit Varma
Differences in Ocular Biometric Measurements among Subtypes of Primary Angle Closure Disease: The Chinese American Eye Study
Ophthalmology Glaucoma, 2021. -
Liyang Hao*, Siqi Liang*, Jinmian Ye, Zenglin Xu (* equal contribution in random order)
TensorD: A tensor decomposition library in TensorFlow
Neurocomputing, 2018. [Code]
-
Open-source Federated Learning Framework Project [Code] [Benchmark] [Docs]
Mentor: Prof. Zenglin Xu
I lead our development team! Our FedLab has 400 stars now. -
Surgery Analysis Project
Mentor: Prof. Yan Liu, Dr. Andrew J Hung
Melady Lab, Viterbi School of Engineering, USC
Keck School of Medicine of USC
-
Large-Scale Data Mining Algorithm Implemantation & Apache Spark [Detail]
INF 553 Course Project, USC
In most cases, my implementation achieves at least 10.0x speed up compared with TA's benchmark with same or even beter performance. -
Angle Closure Glaucoma Detection
Mentor: Dr. Benjamin Y. Xu
Keck School of Medicine of USC
-
Large-scale Tensor Decomposition [Code] [Docs]
Mentor: Prof. Zenglin Xu
SMILE Lab, UESTC
I was responsible for developing the tensor decomposition algorithms in Python and TensorFlow, and documentation. Our open-source Python library based on TensorFlow TensorD has 82 stars now.
-
Research Assistant in Rich Media Big Data Analytics and Application Key Laboratory
Shenzhen Research Institute (SZRI), The Chinese University of Hong Kong
Mentor: Prof. Irwin King
Dec. 2021 – Jun. 2022
-
Research Assistant
SMILE Lab, Shenzhen
Mentor: Prof. Zenglin Xu
Mar. 2021 – Now
-
Graduate Student Researcher in Keck School of Medicine of the University of Southern California
Mentor: Dr. Benjamin Y. Xu
Aug. 2018 – Jun. 2020
-
The Chinese University of Hong Kong (CUHK) Summer Research Placement Programme
Mentor: Prof. Irwin King
Jul. 2017 – Aug. 2017
Subreviewer: NeurIPS 2023, KDD 2022, ACL 2022, EMNLP 2021
Volunteer: KDD 2023 FL4Data-Mining Workshop