About Me
Hi! I am a 4th year PhD student of Electrical and Computer Engineering at Purdue University, West Lafayette. My advisor is Prof. Qiang Qiu.
Previously, I got my M.S. from Carnegie Mellon University, Pittsburgh. I was advised by Prof. Radu Marculescu in 2019 and worked at CyLab with Prof. Raj Rajkumar in 2020.
I earned my B.S. and M.S. from Nanjing University in 2015 and 2018 respectively.
Research Interest
- Representation Learning: Model decomposition, Sparse coding
- Unsupervised Learning: Diffusion model, Optimal transportation
- Federated Learning: Non-IID data, Model aggregation methods
- Continual Learning: Catastrophic forgetting, Model ensemble
- Autonomous Driving
Experience
- Amazon.com, Inc. (2024.5-2024.8), Applied Scientist
Publications
Preprints
- Taewook Kim, Wei Chen, and Qiang Qiu, Learning to Customize Text-to-Image Diffusion In Diverse Context”, (2024) arXiv preprint arXiv:2410.10058, Paper
Conference
-
Zichen Miao, Wei Chen, and Qiang Qiu, Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Models, (2025) Computer Vision and Pattern Recognition Conference, Paper
-
Wei Chen, Zichen Miao, and Qiang Qiu, Large convolutional model tuning via filter subspace, (2025) International Conference on Learning Representations, Paper
-
Wei Chen, Zichen Miao, Qiang Qiu, Inner Product-based Neural Network Similarity, NeurIPS (2023) Project Page, Paper
-
Atul Sharma, Wei Chen, Joshua Zhao, Qiang Qiu, Saurabh Bagchi, Somali Chaterji. Flair: Defense against model poisoning attack in federated learning, (2023) ACM Asia Conference on Computer and Communications Security, Paper
-
Atul Sharma, Joshua C Zhao, Wei Chen, Qiang Qiu, Saurabh Bagchi, Somali Chaterji, How to Learn Collaboratively-Federated Learning to Peer-to-Peer Learning and What’s at Stake, (2023) 53rd IEEE/IFIP International Conference on Dependable Systems and Networks-Supplemental Volume (DSN-S), Paper
-
Zichen Miao, Ze Wang, Wei Chen, Qiang Qiu: Continual Learning with Filter Atom Swapping, (2022) International Conference on Learning Representations (ICLR), Paper
-
I Beak, W Chen, Z Zhu, S Samii, R Rajkumar: FT-DeepNets: Fault-Tolerant Convolutional Neural Networks with Kernel-based Duplication, (2022) IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Paper
-
J Lezama, W Chen, Q Qiu: Run-Sort-ReRun: Escaping Batch Size Limitations in Sliced Wasserstein Generative Models, (2021) International Conference on Machine Learning (ICML), 6275-6285, Paper
-
I Beak, W Chen, A Venkat, R Rajkumar: Practical Object Detection Using Thermal Infrared Image Sensors, (2021) IEEE Intelligent Vehicles Symposium (IV) workshop, Paper
-
K Bhardwaj, W Chen, R Marculescu: New directions in distributed deep learning: bringing the network at forefront of IoT design, (2020) 57th ACM/IEEE Design Automation Conference (DAC), 1-6, Paper
-
W Chen, K Bhardwaj, R Marculescu: Fedmax: mitigating activation divergence for accurate and communication-efficient federated learning, (2020) ECML PKDD, Lecture Notes in Computer Science, vol 12458. Springer, Cham. Paper
News
- May, 2024: I start my internship at Amazon as Applied Scientist.
- May, 2024: I have passed my preliminary exam, and officially become PhD candidate.
- Sep, 2023: Our paper Inner Product-based Neural Network Similarity is accepted by NeurIPS.
- July, 2023: I served as a reviewer for NeurIPS
- Mar, 2023: I served as a reviewer for ICML
- Jan, 2023: I served as a reviewer for CVPR
- Jan, 2023: I am now TA for ECE-50024, Machine Learning
- Aug, 2022: I am now TA for ECE-57000, Artificial Intelligence
- July, 2022: I served as a reviewer for NeurIPS
- May, 2022: I served as a reviewer for ECCV
- April, 2022: I served as a PC reviewer for CVPR workshop, Vision Datasets Understanding
- Jan, 2022: I served as a reviewer for CVPR
- Aug, 2021: I joined QLab at Purdue University, working with professor Qiang Qiu.