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@Michigan State University (MSU), advised by Dr. Jiayu Zhou. Previously, I obtained my B.S. in Physics and M.S. in Computer Science at University of Science and Technology of China (USTC). Also, I am fortunate to work closely with Dr. Zhangyang Wang.

My research centers around privacy-preserving learning and expands to Inclusive and Trustworthy Machine Learning. I am interested in enhancing trustworthiness (regarding fairness, robustness and security) under the privacy constraint, e.g., federated learning and differentially-private learning.

[Privacy] in centralized learning with theoretic understanding and empirical algorithms, distributed learning, and outsourcing training.
[Fair] pre-training and federated learning.
[Robustness] for heterogenous devices, against OoD inference in federated learning.
[Secure] learning against backdoor attacks.
[Affordable] efficient on-device model adaptation and customizable federated learning for low-end devices.

I am on the job market! Please feel free to contact me and check my curricula vitae.

News

[March, 2022] We are going to organize a KDD workshop on federated learning for distributed data mining. More details are coming soon.
[Jan, 2023] Two papers got accepted to ICLR'23: OoD detection by FL (spotlight!), memory-efficient CTA.
[Sep, 2022] Our work on federated robustness sharing has been accepted to AAAI'23 (oral).
[Nov, 2022] Two papers got accepted to NeurIPS'22: outsourcing training, backdoor defense.

[May, 2022] Our work on connection-resilient FL got accepted to ICML'22.

Interests

Trustworthy Machine Learning
Privacy
Federated Learning

Education

PhD in CSE, 2023 (expected)

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.

Haotao Wang, Junyuan Hong, Jiayu Zhou, Zhangyang Wang. How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts. TMLR, 2023.

Haobo Zhang, Junyuan Hong, Fan Dong, Steve Drew, Liangjie Xue, Jiayu Zhou. A Privacy-Preserving Hybrid Federated Learning Framework for Financial Crime Detection. Preprint, 2023.

Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger. MECTA: Memory-Economic Continual Test-Time Model Adaptation. ICLR, 2023.

Shuyang Yu, Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou. Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection. ICLR (spotlight), 2023.

Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou. Federated Robustness Propagation: Sharing Adversarial Robustness in Federated Learning. AAAI (oral), 2023.

Junyuan Hong, Haotao Wang, Haobo Zhang, Zhangyang Wang, Jiayu Zhou. Precautionary Unfairness in Self-Supervised Contrastive Pre-training. Preprint, 2022.

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

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.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Federated Adversarial Debiasing for Fair and Trasnferable Representations

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]
‘Dynamic Policies on Differential Private Learning’ @ VITA Seminars, UT Austin, Sep, 2020: [slides]

Teaching Assistant

CSE 847: Machine Learning, 2021
CSE 404: Introduction to Machine Learning, 2020

Award

Dissertation Completion Fellowship, MSU, 2023
Carl V. Page Memorial Graduate Fellowship, MSU, 2021
Student Travel Award, KDD, 2018
Outstanding Freshman Scholarship, USTC, 2015

Service

External Reviewer: ICML2023, KDD2023, ICLR2023, NeurIPS2022, ICML2022, KDD2022, WSDM2022, AISTATS2022, AAAI2022, AAAI2021, IJCAI2019, NeuroComputing, TKDD
Volunteer: Volunteer in KDD2018, KDD2021