Zuan Xie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zuan Xie has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Hongli Xu
School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China
2 shared publications - Yang Xu
School of Computer Science and Technology, University of Science and Technology of China, Hefei, China
2 shared publications - Yunming Liao
School of Computer Science and Technology, University of Science and Technology of China, Hefei, China
2 shared publications - Zhiwei Yao
School of Computer Science and Technology, University of Science and Technology of China, Hefei, China
2 shared publications - Zihuai Xu
School of Computer Science and Technology, University of Science and Technology of China, Hefei, China
1 shared publication
Latest Publications
- 15 January 2026
- Published by Elsevier in Computer Networks
- Vol. 277
Decentralized federated learning with vertical model parallelism and topology construction
- 15 January 2026
- Published by Elsevier in Computer Networks
- Vol. 277
Decentralized federated learning with vertical model parallelism and topology construction
- 6 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (4) , 5377-5392
Lightweight and Post-Training Structured Pruning for On-Device Large Language Models
Considering the hardware-friendly characteristics, structured pruning has emerged as an effective solution to reduce the resource requirements of large language models (LLMs) on resource-constrained devices. Since pruning a certain number of parameters will often reduce the model accuracy, fine-tuning is usually required to recover performance loss. However, fine-tuning relies on high device power and substantial data, making it unsuitable for on-device applications. Recent approaches propose post-training structured pruning techniques that do not require fine-tuning, following three granularities, i.e., neurons, attention heads, and layers. Unfortunately, the previous solutions still suffer from the high memory overhead of substructures’ importance evaluation at different granularities and the problem of only applying to models with specific structures, which limit their scope of applications. This paper proposes COMP, a lightweight and general post-training structured hybrid-granularity pruning method designed for on-device applications. COMP begins by assessing the importance of model layers and neurons individually using distributional distance and the matrix condition number. Subsequently, COMP performs fine-grained neuron pruning and simultaneously determines whether to apply coarse-grained layer pruning or not by comparing the outcomes of the two granularity strategies. Furthermore, COMP implements mask tuning to restore model accuracy without additional fine-tuning, minimizing dependency on external data resources and device power. Experimental results demonstrate that COMP performs well across models with various architectures. When pruning 20% of LLaMA-2-13B parameters, COMP requires less than 8 GB of memory, maintaining more than 90% model accuracy. Meanwhile, COMP improves performance by 3.54% compared to LLM-Pruner, while reducing memory overhead by 90%.
- 6 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (4) , 5377-5392
Lightweight and Post-Training Structured Pruning for On-Device Large Language Models
Considering the hardware-friendly characteristics, structured pruning has emerged as an effective solution to reduce the resource requirements of large language models (LLMs) on resource-constrained devices. Since pruning a certain number of parameters will often reduce the model accuracy, fine-tuning is usually required to recover performance loss. However, fine-tuning relies on high device power and substantial data, making it unsuitable for on-device applications. Recent approaches propose post-training structured pruning techniques that do not require fine-tuning, following three granularities, i.e., neurons, attention heads, and layers. Unfortunately, the previous solutions still suffer from the high memory overhead of substructures’ importance evaluation at different granularities and the problem of only applying to models with specific structures, which limit their scope of applications. This paper proposes COMP, a lightweight and general post-training structured hybrid-granularity pruning method designed for on-device applications. COMP begins by assessing the importance of model layers and neurons individually using distributional distance and the matrix condition number. Subsequently, COMP performs fine-grained neuron pruning and simultaneously determines whether to apply coarse-grained layer pruning or not by comparing the outcomes of the two granularity strategies. Furthermore, COMP implements mask tuning to restore model accuracy without additional fine-tuning, minimizing dependency on external data resources and device power. Experimental results demonstrate that COMP performs well across models with various architectures. When pruning 20% of LLaMA-2-13B parameters, COMP requires less than 8 GB of memory, maintaining more than 90% model accuracy. Meanwhile, COMP improves performance by 3.54% compared to LLM-Pruner, while reducing memory overhead by 90%.