Hao Yu

Hao Yu

Auto-generated profile, based on publicly available information

Hao Yu

School of Computer Science and School of Cyberspace Science, Xiangtan University, Xiangtan, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
6 January 2025 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
JLJiaye Li
Jiaye Li
JSjiagang song
jiagang song
JSJinjing Shi
Jinjing Shi
HXHang Xu
Hang Xu
HYHao Yu
Hao Yu
SZShichao Zhang
Shichao Zhang
High-dimensional data has long been a notoriously challenging issue. Existing quantum dimension reduction technology primarily focuses on quantum principal component analysis. However, there are only a few studies on quantum feature selection (QFS) algorithms, and these algorithms are often not robust. Additionally, there are limited quantum circuits specifically designed for feature selection, and they still cannot address the objective function based on sparse learning. To address these issues, this article proposes a robust QFS algorithm by designing a novel sparse optimization circuit. Specifically, we first apply sparse regularization and least squares loss to construct the proposed objective function. Then, six types of quantum registers and their initial states are prepared. Furthermore, quantum techniques such as quantum phase estimation and controlled rotation are employed to construct a sparse optimization circuit, which is used to obtain the final quantum state of the feature selection variable. Finally, a series of experiments are conducted to verify the accuracy of the feature selection and the robustness of the proposed algorithm.

7 September 2022 in Mathematics
Verified
Journal Article
Open access
PDF file
YXYingxin Xiang
Yingxin Xiang
CZChengyuan Zhang
Chengyuan Zhang
ZHZhichao Han
Zhichao Han
HYHao Yu
Hao Yu
JLJiaye Li
Jiaye Li
LZlei zhu
lei zhu
Visual question answering (VQA) is regarded as a multi-modal fine-grained feature fusion task, which requires the construction of multi-level and omnidirectional relations between nodes. One main solution is the composite attention model which is composed of co-attention (CA) and self-attention(SA). However, the existing composite models only consider the stack of single attention blocks, lack of path-wise historical memory, and overall adjustments. We propose a path attention memory network (PAM) to construct a more robust composite attention model. After each single-hop attention block (SA or CA), the importance of the cumulative nodes is used to calibrate the signal strength of nodes’ features. Four memoried single-hop attention matrices are used to obtain the path-wise co-attention matrix of path-wise attention (PA); therefore, the PA block is capable of synthesizing and strengthening the learning effect on the whole path. Moreover, we use guard gates of the target modal to check the source modal values in CA and conditioning gates of another modal to guide the query and key of the current modal in SA. The proposed PAM is beneficial to construct a robust multi-hop neighborhood relationship between visual and language and achieves excellent performance on both VQA2.0 and VQA-CP V2 datasets.

20 January 2026 in Knowledge and Information Systems
Verified
Journal Article
Closed access
PDF file
HXHang Xu
Hang Xu
JLJiaye Li
Jiaye Li
HYHao Yu
Hao Yu
JZJian Zhang
Jian Zhang
SZShichao Zhang
Shichao Zhang

15 July 2025 in Information Fusion
Verified
Journal Article
Closed access
HYHao Yu
Hao Yu
SZShichao Zhang
Shichao Zhang
JLJiaye Li
Jiaye Li
CLChengqing Li
Chengqing Li

24 April 2026 in Information Fusion
Verified
Journal Article
Closed access
HYHao Yu
Hao Yu
JLJiaye Li
Jiaye Li
SZShichao Zhang
Shichao Zhang