Junyuan Hong

CSE PhD Student

Michigan State University

Biography

I am currently a final-year Ph.D. student of Computer Science and Engineering at ILLIDAN Lab@MSU, advised by Dr. Jiayu Zhou. Previously, I obtained my B.S. in Physics and M.S. in Computer Science at USTC. My current research interests include Federated Learning and Data Privacy. Check my curricula vitae.

Interests

• Federated Learning
• Privacy
• Manifold Learning

Education

• PhD in Computer Science&Engineering, Present

  Michigan State University

• MSc in Computer Science, 2018

  University of Science and Technology of China

• BSc in Physics, minor in CS., 2015

  University of Science and Technology of China

Publications

Quickly discover relevant content by filtering publications.

Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou. Federated Robustness Propagation: Sharing Adversarial Robustness in Federated Learning. AAAI, 2022.

Preprint Code Project

Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger. Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling. NeurIPS, 2022.

PDF Project Slides

Haotao Wang, Junyuan Hong, Aston Zhang, Jiayu Zhou, Zhangyang Wang. Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork. NeurIPS, 2022.

PDF Code

Zhuangdi Zhu, Junyuan Hong, Steve Drew, Jiayu Zhou. Resilient and Communication Efficient Learning for Heterogeneous Federated Systems. ICML, 2022.

PDF Project

Junyuan Hong, Zhangyang Wang, Jiayu Zhou. Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent. FAccT, 2022.

Preprint Project Slides

Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou. Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization. ICLR, 2022.

PDF Code Project Slides Video

Junyuan Hong, Zhuangdi Zhu, Shuyang Yu, Hiroko Dodge, Zhangyang Wang, Jiayu Zhou. Federated Adversarial Debiasing for Fair and Trasnferable Representations. KDD (Oral), 2021.

PDF Code Project Slides Video DOI

Zhuangdi Zhu, Junyuan Hong, Jiayu Zhou. Data-Free Knowledge Distillation for Heterogeneous Federated Learning. ICML, 2021.

Preprint Code Project

Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou. Learning Model-Based Privacy Protection under Budget Constraints. AAAI, 2021.

PDF Project Slides Video Supplementary

Junyuan Hong, Yang Li, Huanhuan Chen. Variant Grassmann Manifolds: A Representation Augmentation Method for Action Recognition. TKDD, 2019.

PDF Project DOI

Yang Li, Junyuan Hong, Huanhuan Chen. Short Sequence Classification Through Discriminable Linear Dynamical System. TNNLS, 2019.

DOI

Junyuan Hong, Huanhuan Chen, Feng Lin. Disturbance Grassmann Kernels for Subspace-Based Learning. KDD (Oral), 2018.

PDF Cite Project Video DOI Supplementary

Yang Li, Junyuan Hong, Huanhuan Chen. Sequential Data Classification in the Space of Liquid State Machines. ECML, 2016.

PDF Code

Featured Publications

Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling

We propose a new privacy-preserving learning framework, outsourcing training to cloud without uploading data, which provides more data without injecting noise into gradient or samples.

Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger

PDF Project Slides

Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization

Efficient and federated learning for heterogeneous clients with different memory sizes

Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou

PDF Code Project Slides Video

Federated Adversarial Debiasing for Fair and Trasnferable Representations

A distributed domain/group debiasing framework for unsupervised domain adaptation or fairness enhancement.

Junyuan Hong, Zhuangdi Zhu, Shuyang Yu, Hiroko Dodge, Zhangyang Wang, Jiayu Zhou

PDF Code Project Slides Video DOI

Professional Activities

Internship

• Research Intern with Dr. Lingjuan Lyu, Sony AI, 2022

Talks

• ‘Split-Mix Federated Learning for Model Customization’ @ TrustML Young Scientist Seminars, July, 2022: [link] [video]
• Federated Adversarial Debiasing for Fair and Transferable Representations, @ CSE Graduate Seminar, Michigan State University, October, 2021: [slides]

Teaching Assistant

• CSE 404: Introduction to Machine Learning, 2020 Fall

Award

• Carl V. Page Memorial Graduate Fellowship, MSU, 2021
• Student Travel Award, KDD, 2018
• Outstanding Freshman Scholarship, USTC, 2015

Service

• External Reviewer: ICLR2023, NeurIPS2022, ICML2022, KDD2022, WSDM2022, AISTATS2022, AAAI2022, AAAI2021, IJCAI2019, NeuroComputing, TKDD
• Volunteer: Volunteer in KDD2018, KDD2021

Projects

*

All Machine Learning Other

Federated Learning

On the need of data privacy and more data, we strive to join the knowledge from a fair amount of users to train powerful deep neural networks without sharing data.

Differentially Private Learning

On the concern of data privacy, we aim to develop algorithms towards learning accurate models privately from data.

Subspace Learning

Supervised learning on subspace data which could model real data like skeleton motion.

Recent Posts

Evaluate Binary Classification with Keras

Keras provides very convenient tools for fast protyping Machine Learning models, especially neural networks. You can pass metric functions when compiling a model, to evaluate the learnt models. However in the current version (after v2.

Junyuan Hong

Nov 15, 2018 3 min read machine-learning

Python Decorator

When refactoring a codes, we need to extract duplicated features from different methods or functions. A magic in Python 3 is to decorate the a striped basic functions with sharing features.

Junyuan Hong

Nov 15, 2018 1 min read tech

Linux Rookie Book

As a MS student, I am going to leave my lab at USTC. With this post, I’d like to share my experiences on the Linux system, especially for those who are new to such a system.

Jun 11, 2018 4 min read How-to

See all posts