Zhenyu Shi

Zhenyu Shi

Auto-generated profile, based on publicly available information

Zhenyu Shi

Beijing University of Technology

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
11 July 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
ZCZhihua Cui
Zhihua Cui
ZSZhenyu Shi
Zhenyu Shi
QLQi Li
Qi Li
TZTianhao Zhao
Tianhao Zhao
WZWensheng Zhang
Wensheng Zhang
JCJinjun Chen
Jinjun Chen

15 December 2023
Verified
Conference Paper
Open access
BDBo Dong
Bo Dong
YXYiming Xu
Yiming Xu
SCSunyi Chi
Sunyi Chi
ZSZhenyu Shi
Zhenyu Shi
ZDZheng Du
Zheng Du
Practical natural language processing (NLP) tasks often exhibit long-tailed distributions accompanied by noisy labels, posing significant challenges to the generalization and robustness of complex models such as Deep Neural Networks (DNNs). Traditional resampling techniques like oversampling or undersampling, while commonly employed, can easily lead to overfitting. A growing trend involves leveraging small amounts of metadata to learn data weights, alongside the demonstrated benefits of self-supervised pre-training, particularly for under-represented data. In this work, we propose a general framework that addresses both the long-tail and noisy label issues. Our model is adaptively tailored to the problem domain using a contrastive learning approach. The re-weighting module, a feed-forward network, learns explicit weighting functions and adjusts weights based on metadata. Additionally, our framework modifies the weights of terms in the loss function through a combination of polynomial expansion of the cross-entropy loss and focal loss. Extensive experiments consistently demonstrate the superior performance of our proposed framework compared to baseline methods. Finally, our comprehensive sensitivity analysis underscores the efficacy of the proposed framework in handling long-tailed problems and mitigating the adverse effects of noisy labels.

1 January 2026 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
MLMengxia Li
Mengxia Li
Juan FangJuan Fang
Juan Fang
ZSZhenyu Shi
Zhenyu Shi
NHNan He
Nan He
XZXiaoning Zhai
Xiaoning Zhai
MZMengyuan Zhang
Mengyuan Zhang

1 January 2026 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
ZSZhenyu Shi
Zhenyu Shi
Juan FangJuan Fang
Juan Fang
MLMengxia Li
Mengxia Li
QMQi Ming
Qi Ming
MZMengyuan Zhang
Mengyuan Zhang
Neal XiongNeal Xiong
Neal Xiong

23 February 2026 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
Juan FangJuan Fang
Juan Fang
HTHeng Tang
Heng Tang
ZTZiyi Teng
Ziyi Teng
ZSZhenyu Shi
Zhenyu Shi
SWShen Wu
Shen Wu
HCHuijie Chen
Huijie Chen
In collaborative inference scenarios, semantic communication replaces raw data transmission by conveying task-oriented semantic features to improve bandwidth efficiency. However, under noisy wireless channels, the combined effects of semantic compression distortion and channel noise lead to severe information loss, resulting in degraded inference accuracy. To address this issue, this article proposes a multiscale semantic compression collaborative inference (MSCCI) framework that achieves efficient, stable inference performance under high compression ratios (CRs) and elevated noise levels. Specifically, a UNet-based encoder extracts multiscale semantic features on an IoT device. These features are then integrated into a unified stream using a novel semantic fusion compression strategy, thereby substantially reducing communication overhead. The edge server decoder decompresses features and recovers image semantics via progressive upsampling and multiscale semantic restoration. For noisy wireless channels, the framework incorporates squeeze-and-excitation (SE) attention for dynamic feature channel weighting and residual connections for enhanced low-SNR robustness. Experimental results demonstrate that our collaborative inference framework for semantic communication outperforms state-of-the-art algorithms, and the approach’s effectiveness and robustness are verified across various channel conditions.