I am currently a PhD student in the Intelligent and Distributed Computing (IDC) Laboratory of Huazhong University of Science and Technology (HUST), under the supervision of Prof. Yuhua Li and Prof. Ruixuan Li. Before joining HUST, I got my bachelorβs degree in Beijing University of Posts and Telecommunications (BUPT).
My research interest includes Model Compression and Acceleration, and their applications in Recommender Systems, Federated Learning, and more. Recently, I have been working on Parameter-Efficient Fine-Tuning and Inference Acceleration for LLMs.
π₯ News
- 2024.07: Β ππ One paper was accepted by MM 2024.
- 2024.05: Β ππ One paper was accepted by ICML 2024.
π Publications
- Shiwei Li, Yingyi Cheng, Haozhao Wangβ , Xing Tang, Shijie Xu, Weihong Luo, Yuhua Li, Dugang Liu, Xiuqiang He, Ruixuan Li. Masked Random Noise for Communication-Efficient Federated Learning. The 32nd ACM International Conference on Multimedia (ACM MM), Melbourne, Australia, 28th October - 1st November, 2024. (CCF-A) [paper] [code]
- Shiwei Li, Wenchao Xu, Haozhao Wangβ , Xing Tangβ , Yining Qi, Shijie Xu, Weihong Luo, Yuhua Li, Xiuqiang He, Ruixuan Liβ . FedBAT: Communication-Efficient Federated Learning via Learnable Binarization. The Forty-first International Conference on Machine Learning (ICML), Vienna, Austria, 21st-27th July, 2024. (CCF-A) [paper] [code]
- Shiwei Li*, Huifeng Guo*, Xing Tang, Ruiming Tang, Lu Hou, Ruixuan Liβ , Rui Zhangβ . Embedding Compression in Recommender Systems: A Survey. ACM Computing Surveys, 2024, 56(5): 1-21. (Q1, IF=23.8) [paper]
- Shiwei Li, Huifeng Guo, Lu Hou, Wei Zhang, Xing Tang, Ruiming Tang, Rui Zhangβ , Ruixuan Liβ . Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction. Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), Washington, DC, USA, February 7-14, 2023. (CCF-A) [paper] [code]
π Preprint
- Shiwei Li, Zhuoqi Hu, Xing Tang, Haozhao Wang, Shijie Xu, Weihong Luo, Yuhua Li, Xiuqiang He, Ruixuan Liβ . Mixed-Precision Embeddings for Large-Scale Recommendation Models. [paper] [code]
π Educations
- 2021.09 - 2026.06 (expected), Ph.D. in Huazhong University of Science and Technology (HUST).
- 2017.09 - 2021.06, B.S. in Beijing University of Posts and Telecommunications (BUPT).
π» Internships
- 2023.06 β 2024.06, [Tencent Financial Technology (FiT)], Shenzhen, China, under the supervision of Shijie Xu, Weihong Luo, Xing Tang and Xiuqiang He.
- 2021.10 β 2022.09, [Huawei Noahβs Ark Lab], Shenzhen, China, under the supervision of Huifeng Guo, Lu Hou, Ruiming Tang and Rui Zhang.