Shen-Huan Lyu

Shen-Huan Lyu

Assistant Researcher

Hohai University

Biography

Enrolling Students: Looking for self-motivated M.Sc/Ph.D. students to work on Artificial Intelligence. Feel free to send me an email with your CV.

I am an Assistant Researcher in College of Computer Science & Software Engineering at Hohai University. I obtained my Ph.D. degree from Department of Computer Science & Technology in Nanjing University in Dec. 2022, where I was very fortunate to be advised by Prof. Zhi-Hua Zhou. Before that, I received my B.Sc. degree from Department of Statistics in University of Science and Technology of China in Jun. 2017.

Download my resume.

Interests
  • Ensemble Learning
  • Learning Theory and Optimization
Education

  • Ph.D. in Computer Science, 2017-2022

    Nanjing University (NJU)

  • B.Sc. in Statistics, 2013-2017

    University of Science and Technology of China (USTC)

Experience

 
 
 
 
 
Hohai University
Assistant Researcher
Hohai University
Dec 2022 – Dec 2024 Nanjing
 
 
 
 
 
Huawei Noah's Ark Lab
Machine Learning Engineer
Huawei Noah’s Ark Lab
Jun 2022 – Aug 2022 Nanjing
 
 
 
 
 
Nanjing University
Ph.D.
Nanjing University
Sep 2017 – Dec 2022 Nanjing
 
 
 
 
 
University of Science and Technology of China
B.Sc.
University of Science and Technology of China
Sep 2013 – Jun 2017 Hefei

Recent Publications

Quickly discover relevant content by filtering publications.
Yi-Xiao He, Shen-Huan Lyu, Yuan Jiang (2024). Interpreting Deep Forest through Feature Contribution and MDI Feature Importance. In ACM Transactions on Knowledge Discovery from Data, in press.

PDF Cite arXiv

Shen-Huan Lyu, Yi-He Chen, Yuan Jiang (2023). Interaction Representations Based Deep Forest Method in Multi-Label Learning. In Journal of Software, in press.

PDF Cite DOI

Qin-Cheng Zheng, Shen-Huan Lyu, Shao-Qun Zhang, Yuan Jiang, Zhi-Hua Zhou (2023). On the Consistency Rate of Decision Tree Learning Algorithms. In Proceedings of the 26th International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 7824-7848, Valencia, ES.

PDF Cite DOI

Shen-Huan Lyu, Yi-Xiao He, Zhi-Hua Zhou (2022). Depth is More Powerful than Width with Prediction Concatenation in Deep Forests. In Advances in Neural Information Processing Systems 35 (NeurIPS Oral), pp. 29719-29732, New Orleans, US.

PDF Cite DOI

Shen-Huan Lyu, Yi-He Chen, Zhi-Hua Zhou (2022). A Region-Based Analysis for the Feature Concatenation in Deep Forests. In Chinese Journal of Electronics, 31(6):1072-1080.

PDF Cite DOI

Shen-Huan Lyu, Lu Wang, Zhi-Hua Zhou (2022). Improving Generalization of Deep Neural Networks by Leveraging Margin Distributions. In Neural Networks, 151:48-60.

PDF Cite DOI

Yi-He Chen, Shen-Huan Lyu, Yuan Jiang (2021). Improving Deep Forest by Exploiting High-Order Interactions. In Proceedings of the 21th IEEE International Conference on Data Mining (ICDM), pp. 1030-1035, Auckland, NZ.

PDF Cite DOI

Shen-Huan Lyu, Liang Yang, Zhi-Hua Zhou (2019). A Refined Margin Distribution Analysis for Forest Representation Learning. In Advances in Neural Information Processing Systems 32 (NeurIPS), pp. 5531-5541, Vancouver, CA.

PDF Cite DOI

Recent & Upcoming Talks

Depth is More Powerful than Width
This is an oral representation related to the paper “Depth is More Powerful than Width with Prediction Concatenation in Deep Forest”.
Dec 8, 2022 1:00 PM — 3:00 PM New Orleans Convention Center, Online
Lyu Shen-Huan
Depth is More Powerful than Width
Margin Distribution Neural Networks
This is a talk related to the paper “Improving Generalization of Deep Neural Networks by Leveraging Margin Distributions”.
Jun 1, 2022 1:00 PM — 3:00 PM Huawei Noah's Ark Lab, Online
Lyu Shen-Huan
Margin Distribution Neural Networks
Margin Distribution Deep Forest
This is a talk related to the paper “A Refined Margin Distribution Analysis for Forest Representation Learning”.
Dec 8, 2019 1:00 PM — 3:00 PM Vancouver Convention Center
Lyu Shen-Huan
Margin Distribution Deep Forest

Teaching

Academic Service

Senior Program Committee Member of Conferences:

  • IJCAI: 2021

Program Committee Member of Conferences:

  • ICML: 2021, 2022, 2023
  • NeurIPS: 2020,2021, 2022
  • AAAI: 2020, 2021
  • IJCAI: 2020, 2022, 2023
  • ICLR: 2020, 2021, 2022

Reviewer for Journals:

  • Artificial Intelligence (AIJ)
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • IEEE Transactions on Knowledge and Data Engineering (TKDE)
  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
  • ACM Transactions on Knowledge Discovery from Data (TKDD)
  • Machine Learning (MLJ)
  • Research
  • Chinese Journal of Electronics (CJE)
  • 软件学报 (Journal of Software, JOS)

Awards & Honors

  • Artificial Intelligence Scholarship in Nanjing University , Nanjing, 2019
  • The First Class Academic Scholarship in Nanjing University , Nanjing, 2018-2019
  • Presidential Special Scholarship for first year Ph.D. Student in Nanjing University , Nanjing, 2017
  • The University Silver Prize Scholarship for Excellent Student in University of Science and Technology of China , Hefei, 2014-2016

Keywords

computational complexity consistency deep forest deep neural networks desicion tree ensemble learning feature importance generalization bound interaction interpretability label correlation margin theory multi-label learning overfitting region theory representation learning