Bio
I am an Assistant Professor (Principal investigator, PhD supervisor) in the Department of Statistics and Data Science at SUSTech (China, Shenzhen). I obtained my Ph.D. degree at the School of Computer Science and Engineering, Nanyang Technological University, supervised by Prof. Bo An.
During my Ph.D, I was fortunate to work as a visiting scholar in the group of Prof. Sharon Yixuan Li at the University of Wisconsin Madison in 2022.
Previously I spent a wonderful year as a research assistant in the Institute for Interdisciplinary Information Sciences at Tsinghua University.
Prior to that, I received my B.E. in Software Engineering from Huazhong University of Science and Technology in 2016.
My research interest falls in the scope of Natural Robustness, which preserves model performance under naturally induced data corruptions or alterations across the machine learning pipeline.
The goal of my research is to build a reliable learning system, which can work safely and adaptively in the presence of unexpected data conditions across the entire pipeline.
My research is closely related to data-centric machine learning and foundation model, including:
Data quality: label noise, outliers, malicious data;
Data efficiency: data valuation, data selection;
Data privacy: membership inference attack, machine unlearning;
Reliable AI: conformal prediction, learning with rejection, confidence calibration (For LLM: harmless & honesty);
News
March 2024
I will be serving as a Area Chair for NeurIPS 2024.
January 2024
Three papers are accepted by ICLR 2024 (Two are Spotlights).
December 2023
We release a Python toolbox for conformal prediction research
TorchCP.
May 2023
I am always looking for highly-motivated research interns, RAs and PostDocs to join our research (refer to
this page). Mphil or PhD applications (2024 or 2025 fall) are also welcome.
May 2022
Two papers are accepted by ICML 2022 (Accept rate: 21.9%).
Working papers
TorchCP: A Library for Conformal Prediction based on PyTorch
Hongxin Wei, Jianguo Huang
Does Confidence Calibration Help Conformal Prediction?
Huajun Xi, Jianguo Huang, Lei Feng, Hongxin Wei *
Conformal Prediction for Deep Classifier via Label Ranking
Jianguo Huang, Huajun Xi, Linjun Zhang, Huaxiu Yao, Yue Qiu, Hongxin Wei *
Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
Zhenlong Liu, Lei Feng, Huiping Zhuang, Xiaofeng Cao, Hongxin Wei *
Exploring Learning Complexity for Downstream Data Pruning
Wenyu Jiang, Zhenlong Liu, Zejian Xie, Songxin Zhang, Bingyi Jing, Hongxin Wei *
Open-Vocabulary Calibration for Vision-Language Models
Shuoyuan Wang, Jindong Wang, Guoqing Wang, Bob Zhang, Kaiyang Zhou, Hongxin Wei *
MetaInfoNet: Learning Task-Guided Information for Sample Reweighting
Hongxin Wei, Lei Feng, Rundong Wang, Bo An
Selected Publications
CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning
CVPR 2024
Shiyu Tian, Hongxin Wei, Yiqun Wang, Lei Feng
DOS: Diverse Outlier Sampling for Out-of-Distribution Detection
ICLR 2024
Wenyu Jiang, Hao Cheng, MingCai Chen, Chongjun Wang, Hongxin Wei *
Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
ICLR 2024(Spotlight)
Hao Chen, Jindong Wang, Ankit Shah, Ran Tao, Hongxin Wei, Xing Xie, Masashi Sugiyama, Bhiksha Raj
Consistent Multi-Class Classification from Multiple Unlabeled Datasets
ICLR 2024 (Spotlight)
Zixi Wei, Senlin Shu, Yuzhou Cao, Hongxin Wei, Bo An, Lei Feng
Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition.
IMWUT/Ubicomp 2024
Shuoyuan Wang, Jindong Wang, HuaJun Xi, Bob Zhang, Lei Zhang, Hongxin Wei
On the Importance of Feature Separability in Predicting Out-Of-Distribution Error.
NeurIPS 2023
Renchunzi Xie, Hongxin Wei *, Lei Feng, Yuzhou Cao, Bo An
In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer
NeurIPS 2023
Yuzhou Cao, Hussein Mozannar, Lei Feng, Hongxin Wei, Bo An
Regression with Cost-based Rejection
NeurIPS 2023
Xin Cheng, Yuzhou Cao, Haobo Wang, Hongxin Wei, Bo An, Lei Feng
Mitigating Memorization of Noisy Labels by Clipping the Model Prediction
ICML 2023
Hongxin Wei, Huiping Zhuang, Renchunzi Xie, Lei Feng, Gang Niu, Bo An, Yixuan Li
A Generalized Unbiased Risk Estimator for Learning with Augmented Classes
AAAI 2023
Senlin Shu, Shuo He, Haobo Wang,
Hongxin Wei, Tao Xiang,
Lei Feng
Can Adversarial Training Be Manipulated By Non-Robust Features?
NeurIPS 2022
Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection
NeurIPS 2022
Huiping Zhuang, Zhenyu Weng, Hongxin Wei, Renchunzi Xie, Toh Kar-Ann, Zhiping Lin
Mitigating Neural Network Overconfidence with Logit Normalization
ICML 2022
Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets
ICML 2022
Deep Learning from Multiple Noisy Annotators as A Union
TNNLS
Hongxin Wei, Renchunzi Xie, Lei Feng, Bo An
GearNet: Stepwise Dual Learning for Weakly Supervised Domain Adaptation
AAAI 2022
Renchunzi Xie, Hongxin Wei *, Lei Feng, Bo An
Open-set Label Noise Can Improve Robustness Against Inherent Label Noise
NeurIPS 2021
Hongxin Wei, Lue Tao, Renchunzi Xie, Bo An
Multiple-Instance Learning from Similar and Dissimilar Bags
SIGKDD 2021
Lei Feng, Senlin Shu, Yuzhou Cao, Lue Tao, Hongxin Wei, Tao Xiang, Bo An, Gang Niu
Commission Fee is not Enough: A Hierarchical Reinforced Framework for Portfolio Management
AAAI 2021
Rundong Wang †, Hongxin Wei †, Bo An, Zhouyan Feng, Jun Yao
Embedding-Augmented Generalized Matrix Factorization for Recommendation with Implicit Feedback
IEEE Intelligent Systems (IEEE-IS)
Lei Feng, Hongxin Wei *, Qingyu Guo, Zhuoyi Lin, Bo An
Combating noisy labels by agreement: A joint training method with co-regularization
CVPR 2020
Hongxin Wei, Lei Feng, Xiangyu Chen, Bo An
Research Group
Wenyu Jiang
Research Intern
Ph.D. student at Nanjing University.
Kangdao Liu
Research Intern
Ph.D. student at University of Macau
Hao Zeng
Research Intern
PhD student at Xiamen University
Jianguo Huang
Research Intern
Master student at ShanghaiTech University
Shuoyuan Wang
Research Intern
Master student at University of Macau
Hengxiang Zhang
Research Assistant (Full-time)
Master degree from UESTC
Hongfu Gao
Research Intern, Master student at XJTU
Zhenlong Liu
Master student (2023 fall) at SUSTech
Xuanning Zhou
Undergraduate student at HITSZ
Qiang Hu
Undergraduate student at SUSTech
Zicheng Xie
Undergraduate student at SUSTech
Beier Luo
Undergraduate student at SUSTech
(Incoming master student in 2024 fall)
Huajun Xi
Undergraduate student at SUSTech