Weizhi Xu

Weizhi Xu

Auto-generated profile, based on publicly available information

Weizhi Xu

Shandong Normal University

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 July 2023 in ACM Transactions on Architecture and Code Optimization
Verified
Journal Article
Open access
WXWeizhi Xu
Weizhi Xu
YSYintai Sun
Yintai Sun
SFShengyu Fan
Shengyu Fan
HYHui Yu
Hui Yu
XFXin Fu
Xin Fu
The convolutional neural network (CNN) is an important deep learning method, which is widely used in many fields. However, it is very time consuming to implement the CNN where convolution usually takes most of the time. There are many zero values in feature maps and filters, which leads to redundant calculations and memory accesses if dense methods are used to compute convolution. Many works recently have made use of sparsity to skip the calculations for zero values to reduce the inference time of the CNN. On the graphics processing unit platform, current works cannot fully exploit the sparsity of the feature map and achieve satisfactory performance. Therefore, we design a new parallel strategy to transform the feature map into a new storage format to avoid the redundant computation of zero values on graphics processing units. Also considering the sparsity in the feature map, we propose a fused storage format to combine the convolution operation with the following pooling operation, to further improve the performance. We carry out experiments with mainstream CNN models and achieve better performance compared with cuDNN and cuSPARSE. For VGG-19, ResNet-50, DenseNet-121, and RegNetX-16GF, 1.97×, 2.23×, 2.74×, and 1.58× speedups respectively are obtained over cuDNN. The speedups over cuSPARSE respectively are 2.10×, 1.83×, 2.35×, and 1.35× when only using the first method.

23 March 2023 in ACM Transactions on Asian and Low-Resource Language Information Processing
Verified
Journal Article
Open access
KLKaifang Long
Kaifang Long
HZHan Zhao
Han Zhao
ZSZengzhen Shao
Zengzhen Shao
YCYang Cao
Yang Cao
YGYanfang Geng
Yanfang Geng
HYHui Yu
Hui Yu
Chinese Named Entity Recognition (NER) is an essential task in natural language processing, and its performance directly impacts the downstream tasks. The main challenges in Chinese NER are the high dependence of named entities on context and the lack of word boundary information. Therefore, how to integrate relevant knowledge into the corresponding entity has become the primary task for Chinese NER. Both the lattice LSTM model and the WC-LSTM model did not make excellent use of contextual information. Additionally, the lattice LSTM model had a complex structure and did not exploit the word information well. To address the preceding problems, we propose a Chinese NER method based on the deep neural network with multiple ways of embedding fusion. First, we use a convolutional neural network to combine the contextual information of the input sequence and apply a self-attention mechanism to integrate lexicon knowledge, compensating for the lack of word boundaries. The word feature, context feature, bigram feature, and bigram context feature are obtained for each character. Second, four different features are used to fuse information at the embedding layer. As a result, four different word embeddings are obtained through cascading. Last, the fused feature information is input to the encoding and decoding layer. Experiments on three datasets show that our model can effectively improve the performance of Chinese NER.

1 May 2025 in Expert Systems with Applications
Verified
Journal Article
Closed access
YYYaoyao Yan
Yaoyao Yan
HYHui Yu
Hui Yu
DWDa Wang
Da Wang
JYJing Ye
Jing Ye
FLFangai Liu
Fangai Liu
WXWeizhi Xu
Weizhi Xu

5 November 2025 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
YSYintai Sun
Yintai Sun
SFShengyu Fan
Shengyu Fan
ZYZhenhua Yin
Zhenhua Yin
XSXinkai Song
Xinkai Song
XHXing Hu
Xing Hu
MZMingzhe Zhang
Mingzhe Zhang
Fully Homomorphic Encryption (FHE) enables encrypted data processing on untrusted cloud servers, crucial for privacy-sensitive applications. Despite its potential, performance overheads (about $10,000\times$ slower) limit adoption. ASIC accelerators outperform GPUs/FPGAs by optimizing specific operations but rely on costly 7nm processes and large on-chip memory, hindering cost-effective deployment. Balancing efficiency with manufacturing constraints remains critical. This paper presents TensorFHE+, a GPU-optimized FHE acceleration framework leveraging Tensor Cores to accelerate Number Theoretic Transform (NTT) operations. Key innovations include: 1) Decomposing CKKS kernels into vector/matrix operations for hardware utilization; 2) Vectorized modulo arithmetic; 3) Data layout optimization for memory efficiency. Evaluated on NVIDIA A100, TensorFHE+ outperforms TensorFHE[1] by $1.44\times$ in average (up to $1.69\times$ on ResNet-20) and surpasses prior GPU implementations [2], [3]. The design also demonstrates compatibility with commercial linear algebra accelerators, enabling efficient FHE deployment.

14 November 2025
Verified
Conference Paper
Open access
YSYajing Sun
Yajing Sun
ZSZengzhen Shao
Zengzhen Shao
YLYancong Li
Yancong Li
BDBing Dong
Bing Dong
WXWeizhi Xu
Weizhi Xu

1 January 2026 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
ZPZonglong Pan
Zonglong Pan
GZGuijuan Zhang
Guijuan Zhang
HSHuichao Sun
Huichao Sun
XHXiao Hong
Xiao Hong
WXWeizhi Xu
Weizhi Xu
DLDianjie Lu
Dianjie Lu