Zhenyi Wang
Bio:
I am currently a Postdoctoral Associate at University of Maryland, College Park, working with Prof. Heng Huang. Previously, I received my PhD from Department of Computer Science and Engineering at University at Buffalo, advised by Prof. Mingchen Gao.
Research Interest:
Meta learning, Trustworthy Machine Learning, Continual Learning, Bayesian learning.
My research interests primarily focus on:
Trustworthy Meta-Learning
(1): Uncertainty quantification
(2): Robust to task-distribution shift
(3): Data-free meta-learning
Trustworthy Continual Learning
(1): Distributionally robust continual learning
(2): Corruption-robust continual learning
Internship:
Meta Reality Lab, Research Scientist Intern August 2022-December 2022
Amazon, applied scientist intern (Remote) Sept 2020 – December 2020
work on unsupervised text summarization for product review.
JD.COM AI lab (Remote) June 2020 – August 2020
work on vision-language commonsense reasoning with external commonsense knowledge graph for visual question answering.
Tencent AI lab (Seattle, Washington), NLP researcher intern June 2019 – August 2019
work on faithful text generation from knowledge base, i.e., the information contained in the generated text should match the knowledge triples input.
Research Experience:
AI Lab, State Univeristy of New York at Buffalo, USA September 2018 - Present
Research Assistant, Computer Vision Lab, University of Western Ontario, Canada September 2016 - May 2018
Publication:
Survey:
A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning
Zhenyi Wang, Enneng Yang, Li Shen, Heng Huang
Journal:
Distributionally Robust Memory Evolution with Generalized Divergence for Continual Learning
Zhenyi Wang, Li Shen, Tiehang Duan, Qiuling Suo, Le Fang, Wei Liu, Mingchen Gao
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
Conference:
Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Prompt
Chenxi Liu, Zhenyi Wang, Tianyi Xiong, Ruibo Chen, Yihan Wu, Junfeng Guo, Heng Huang
European Conference on Computer Vision (ECCV), 2024
Training A Secure Model against Data-Free Model Extraction
Zhenyi Wang, Li Shen, Junfeng Guo, Tiehang Duan, Siyu Luan, Tongliang Liu and Mingchen Gao
European Conference on Computer Vision (ECCV), 2024
Defense against Model Extraction Attack by Bayesian Active Watermarking
Zhenyi Wang, Yihan Wu, Heng Huang
International Conference on Machine Learning (ICML) 2024
Representation Surgery for Multi-Task Model Merging
Enneng Yang, Li Shen, Zhenyi Wang, Guibing Guo, Xiaojun Chen, Xingwei Wang, Dacheng Tao
International Conference on Machine Learning (ICML) 2024
Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models
Yongxian Wei, Zixuan Hu, Li Shen, Zhenyi Wang, Yu Li, Chun Yuan, Dacheng Tao
International Conference on Machine Learning (ICML) 2024
Sparse Model Inversion: Efficient Inversion of Vision Transformers with Less Hallucination
Zixuan Hu, Yongxian Wei, Li Shen, Zhenyi Wang, Lei Li, Chun Yuan, Dacheng Tao
International Conference on Machine Learning (ICML) 2024
FREE: Faster and Better Data-Free Meta-Learning
Yongxian Wei, Zixuan Hu, Zhenyi Wang, Li Shen, Chun Yuan, Dacheng Tao
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
A Unified and General Framework for Continual Learning
International Conference on Learning Representations (ICLR), 2024
Zhenyi Wang, Yan Li, Li Shen, Heng Huang
Improving Non-Transferable Representation Learning by Harnessing Content and Style (Spotlight)
International Conference on Learning Representations (ICLR), 2024
Ziming Hong, Zhenyi Wang, Li Shen, Yu Yao, Zhuo Huang, Shiming Chen, Chuanwu Yang, Mingming Gong, Tongliang Liu
AdaMerging: Adaptive Model Merging for Multi-Task Learning
International Conference on Learning Representations (ICLR), 2024
Enneng Yang, Zhenyi Wang, Li Shen, Shiwei Liu, Guibing Guo, Xingwei Wang, Dacheng Tao
Meta-Adaptive Stock Movement Prediction with Two-Stage Representation Learning
Donglin Zhan, Yusheng Dai, Yiwei Dong, Jinghai He, Zhenyi Wang, James Anderson
SIAM International Conference on Data Mining (SDM), 2024
Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training
2023 Conference on Neural Information Processing Systems (NeurIPS)
Zhenyi Wang, Li Shen, Tongliang Liu, Tiehang Duan, Yanjun Zhu, Donglin Zhan, David Doermann, Mingchen Gao
An Efficient Dataset Condensation Plugin and Its Application to Continual Learning
2023 Conference on Neural Information Processing Systems (NeurIPS)
Enneng Yang, Li Shen, Zhenyi Wang, Tongliang Liu, Guibing Guo
Distributionally Robust Cross Subject EEG Decoding
European Conference on Artificial Intelligence (ECAI) 2023
Tiehang Duan, Zhenyi Wang, Gianfranco Doretto, Fang Li, Cui Tao, Donald adjeroh
Data Augmented Flatness-aware Gradient Projection for Continual Learning
International Conference on Computer Vision (ICCV) 2023
Enneng Yang, Li Shen, Zhenyi Wang, Shiwei Liu, Guibing Guo, Xingwei Wang
Learning to Learn from APIs: Black-box Data-free Meta-Learning
International Conference on Machine Learning (ICML), 2023
Zixuan Hu, Li Shen, Zhenyi Wang, Baoyuan Wu, Chun Yuan, Dacheng Tao
MetaMix: Towards Corruption-Robust Continual Learning with Temporally Self-Adaptive Data Transformation
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Zhenyi Wang, Li Shen, Donglin Zhan, Qiuling Suo, Yanjun Zhu, Tiehang Duan, Mingchen Gao
Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learning
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Zixuan Hu, Li Shen, Zhenyi Wang, Tongliang Liu, Chun Yuan, Dacheng Tao
Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions
Zhenyi Wang, Li Shen, Le Fang, Qiuling Suo, Donglin Zhan, Tiehang Duan, Mingchen Gao
European Conference on Computer Vision (ECCV), 2022
Meta-Learning without Data via Wasserstein Distributionally-Robust Model Fusion
Zhenyi Wang, Xiaoyang Wang, Li Shen, Qiuling Suo, Kaiqiang Song, Dong Yu, Yan Shen, Mingchen Gao
The Conference on Uncertainty in Artificial Intelligence (UAI), 2022
Improving Task-free Continual Learning by Distributionally Robust Memory Evolution
Zhenyi Wang, Li Shen, Le Fang, Qiuling Suo, Tiehang Duan, Mingchen Gao
International Conference on Machine Learning (ICML), 2022
Learning to Learn and Remember Super Long Multi-Domain Task Sequence (Oral)
Zhenyi Wang, Li Shen, Tiehang Duan, Donglin Zhan, Le Fang, Mingchen Gao
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Meta Learning on a Sequence of Imbalanced Domains with Difficulty Awareness
Zhenyi Wang, Tiehang Duan, Le Fang, Qiuling Suo, Mingchen Gao.
International Conference on Computer Vision (ICCV), 2021.
Meta-Learning with Neural Tangent Kernels
Yufan, Zhou*, Zhenyi Wang*, Jiayi Xian, Changyou Chen, Jinhui Xu.
The 2021 International Conference on Learning Representations (ICLR), 2021. (* indicate equal contribution)
Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference
Bang An, Jie Lyu, Zhenyi Wang, Chunyuan Li, Changwei Hu, Fei Tan, Ruiyi Zhang, Yifan Hu, Changyou Chen
The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020
Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints
Zhenyi Wang, Xiaoyang Wang, Bang An, Dong Yu, Changyou Chen
Annual Conference of the Association for Computational Linguistics (ACL), 2020
Bayesian Meta Sampling for Fast Uncertainty Adaptation
Zhenyi Wang, Yang Zhao, Ping Yu, Ruiyi Zhang, Changyou Chen
International conference on Learning Representations (ICLR), 2020
Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions.
Zhenyi Wang, Ping Yu, Yang Zhao, Ruiyi Zhang, Yufan Zhou, Junsong Yuan, Changyou Chen
Thirty-fourth AAAI conference on Artificial Intelligence (AAAI), 2020
Preprints:
Location Augmentation for CNN
Zhenyi Wang, Olga Veksler
Services:
Senior Reviewer:
CoLLAs
Program Committee/Reviewer:
ICLR , NeurIPS, ICML, CVPR, ECCV, KDD, ACL, EMNLP, NAACL, AAAI, IJCAI.
Journal Reviewer:
IJCV