Junyuan Hong

Postdoctoral Fellow

IFML & WNCG at UT Austin

I am a postdoctoral fellow hosted by Dr. Zhangyang Wang in the VITA group, Institute for Foundations of Machine Learning (IFML) and Wireless Networking and Communications Group (WNCG) at UT Austin. I obtained my Ph.D. degree from Computer Science and Engineering at ILLIDAN Lab@Michigan State University (MSU), advised by Dr. Jiayu Zhou. Previously, I earned my B.S. in Physics and M.S. in Computer Science at University of Science and Technology of China (USTC).

My long-term research vision is to build a Holistic Trustworthy ML system, including fairness, robustness, security and privacy. My recent research centers around Privacy-Centric Trustworthy Machine Learning where I pursue trustworthiness under the privacy constraint, e.g., federated learning and differentially-private learning:

[Privacy] in centralized learning with theoretic understanding and empirical algorithms and in distributed learning.
[Trustworthiness] ⨉ Privacy: Federated Learning FL and Private Edge-Cloud Collaboration
PECC
.
- Fair pre-training
  PECC
  and federated learningFL.
- Robustness by efficient acquisition against adversarial samplesFL and OoD inferenceFL.
- Secure learning against backdoor attacks in private-data-free distillationFL.
- Inclusive learning by efficient on-device model adaptationPECC, and private outsourcing trainingPECC and customizable federated learningFL for low-end devices.

I am on the job market! Check my curricula vitae and feel free to drop me an email if you are interested.

News

September, 2023 Our work on understanding gradient via inversion influence functions got accepted to NeurIPS'23.
August, 2023 We are organizing a KDD workshop on federated learning for distributed data mining (FL4Data-Mining) on August 7th at Long Beach🌴.
July, 2023 🏅 Honored to receive Research Enhancement Award for organizing FL4DataMining workshop! Thank you to MSU Graduate School!
July, 2023 I am going to travel for ICML 2023 at Hawaii 🌺. Come and talk to me about data-free backdoor!
July, 2023 🎓 I successfully defended my thesis. Many thanks to my collaborators, advisor and committees.
May, 2023 My new website is online with released junyuan-academic-theme including many cool new features.
April, 2023 One paper on data-free backdoor got accepted to ICML'23.
March, 2023 🏆 Our ILLIDAN Lab team just won the 3rd place in the U.S. PETs prize challenge. Media cover by The White House, MSU EGR news and MSU Office of Research and Innovation.

More

Jan, 2022 Two papers got accepted to ICLR'23: OoD detection by FL (splotlight!), 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

Foundation (Language/Vision) Models
Trustworthy Machine Learning
Privacy
Federated Learning

Education

PhD in CSE, 2023

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

Projects

Holistic Trustworthy ML

Instead of isolated properties, we target on a holistic trustworthiness covering every properties in one solution.

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.

Publications

NeurIPS 2023 Understanding Deep Gradient Leakage via Inversion Influence Functions.
Haobo Zhang, Junyuan Hong, Yuyang Deng, Mehrdad Mahdavi, Jiayu Zhou.

Preprint 2023 Safe and Robust Watermark Injection with a Single OoD Image.
Shuyang Yu, Junyuan Hong, Haobo Zhang, Haotao Wang, Zhangyang Wang, Jiayu Zhou.

FL4DM 2023 A Privacy-Preserving Hybrid Federated Learning Framework for Financial Crime Detection.
Haobo Zhang, Junyuan Hong, Fan Dong, Steve Drew, Liangjie Xue, Jiayu Zhou.

FL4DM 2023 FedNoisy: A Federated Noisy Label Learning Benchmark.
Siqi Liang, Jintao Huang, Junyuan Hong, Fan Dong, Dun Zeng, Jiayu Zhou, Zenglin Xu.

ICML 2023 Revisiting Data-Free Knowledge Distillation with Poisoned Teachers.
Junyuan Hong, Yi Zeng, Shuyang Yu, Lingjuan Lyu, Ruoxi Jia, Jiayu Zhou.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Featured Publications

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

Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger

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.

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

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

Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou

Efficient and federated learning for heterogeneous clients with different memory sizes

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

Federated Adversarial Debiasing for Fair and Trasnferable Representations

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

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

Federated Adversarial Debiasing for Fair and Trasnferable Representations

Professional Activities

Internship

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

Talks

‘MECTA: Memory-Economic Continual Test-Time Model Adaptation’ @ Computer Vision Talks, March, 2023: [slides] [video]
‘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]

Media Coverage

At Summit for Democracy, the United States and the United Kingdom Announce Winners of Challenge to Drive Innovation in Privacy-enhancing Technologies That Reinforce Democratic Values, The White House, 2023
Privacy-enhancing Research Earns International Attention, MSU Engineering News, 2023
Privacy-Enhancing Research Earns International Attention, MSU Office Of Research And Innovation, 2023

Teaching Assistant

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

Awards

Research Enhancement Award, MSU, 2023
The 3rd place in the U.S. PETs prize challenge, 2023
Dissertation Completion Fellowship, MSU, 2023
Carl V. Page Memorial Graduate Fellowship, MSU, 2021
Student Travel Award, KDD, 2018
Outstanding Freshman Scholarship, USTC, 2015

Services

Program Chair: FL4Data-Mining workshop@KDD 2023 (Lead Chair)
External Reviewer: NeurIPS2023, ICML2023, ECML-PKDD2023, KDD2023, AISTATS2023, ICLR2023, NeurIPS2022, ICML2022, KDD2022, WSDM2022, AISTATS2022, AAAI2022, AAAI2021, IJCAI2019, NeuroComputing, TKDD, TKDE
Volunteer: Volunteer in KDD2018, KDD2021