Junwei Deng - 邓珺玮

📚️ Second-year Ph.D. Student in Information Sciences @UIUC.
🔬 My advisor is Prof. Jiaqi Ma.

👨🏽‍💻 Machine Learning Engineer @Intel, 2020-2023.
🏫 M.S. in Information @Umich, 2019-2021.
🏫 B.S. in Electrical and Computer Engineering @SJTU, 2016-2020.

🏡 Now I live in Champaign, Illinois.

💡 I am interested in Data-Centric AI and Time Series Modeling.

📧 junweid2 AT illinois DOT edu

Google Scholar  /  GitHub  /  CV

(* Equal Contribution)

Preprint

• Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining.
  Weiyi Wang, Junwei Deng, Yuzheng Hu, Shiyuan Zhang, Xirui Jiang, Runting Zhang, Han Zhao, Jiaqi W. Ma
  [ArXiv]


• Efficient Ensembles Improve Training Data Attribution.
  Junwei Deng*, Ting-Wei Li*, Shichang Zhang, Jiaqi W. Ma
  Preprint.
  [ArXiv]


• Computational Copyright: Towards A Royalty Model for Music Generative AI.
  Junwei Deng, Shiyuan Zhang, Jiaqi W. Ma
  DPFM Workshop at ICLR 2024, Best Paper Award.
  [ArXiv]



Selected Publications

• A Versatile Influence Function for Data Attribution with Non-Decomposable Loss.
  Junwei Deng, Weijing Tang, Jiaqi W. Ma
  ICML 2025.
  [ArXiv]


• Adversarial Attacks on Data Attribution.
  Xinhe Wang, Pingbang Hu, Junwei Deng, Jiaqi W. Ma
  ICLR 2025.
  [ArXiv]


• dattri: A Library for Efficient Data Attribution.
  Junwei Deng*, Ting-Wei Li*, Shiyuan Zhang, Shixuan Liu, Yijun Pan, Hao Huang, Xinhe Wang, Pingbang Hu, Xingjian Zhang, Jiaqi W. Ma
  NeurIPS 2024. (Datasets and Benchmark Track, Spotlight).
  [ArXiv][Project Page ]


• BigDL 2.0: Seamless Scaling of AI Pipelines from Laptops to Distributed Cluster.
  Jason Dai, Ding Ding, Dongjie Shi, Shengsheng Huang, Jiao Wang, Xin Qiu, Kai Huang, Guoqiong Song, Yang Wang, Qiyuan Gong, Jiaming Song, Shan Yu, Le Zheng, Yina Chen, Junwei Deng, Ge Song.
  CVPR 2022 (Demo Track).
  [ArXiv][Project Page ]


• Subgroup Generalization and Fairness of Graph Neural Networks.
  Jiaqi Ma*, Junwei Deng*, Qiaozhu Mei.
  NeurIPS 2021. (Spotlight, top 3%)
  [ArXiv][Code]


• Adversarial Attack on Graph Neural Networks as An Influence Maximization Problem.
  Jiaqi Ma*, Junwei Deng*, Qiaozhu Mei.
  WSDM 2022.
  [ArXiv][Code]