Yang Hua
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yang Hua has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Xiaoning Song
Jiangnan University
10 shared publications - Wenjie Zhang
Jiangnan University
8 shared publications - Xiao-Jun Wu
Jiangnan University
6 shared publications - Zhenhua Feng
School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu, China
5 shared publications - Dong-Jun Yu
Nanjing University of Science and Technology
2 shared publications - Tianyang Xu
Jiangnan University
2 shared publications
Latest Publications
- 21 January 2026
- Published by Springer Nature
- p. 478-491
Medical Vision Language Model With Multi-granularity Alignment and Learning Data Augmentation
- 21 January 2026
- Published by Springer Nature
- p. 478-491
Medical Vision Language Model With Multi-granularity Alignment and Learning Data Augmentation
- 25 August 2025
- Published by Springer Nature in Data Mining and Knowledge Discovery
- Vol. 39 (6) , 1-27
Fastere: a fast framework for entity relation extractions
- 25 August 2025
- Published by Springer Nature in Data Mining and Knowledge Discovery
- Vol. 39 (6) , 1-27
Fastere: a fast framework for entity relation extractions
- Open Access
- 12 December 2024
- Published by Springer Nature in Research Square
Link Prediction via Adversarial Knowledge Distillation and Feature Aggregation
Graph neural networks (GNN) have shown strong performance in link prediction tasks. However, it is susceptible to higher latency due to the trivial correlation of data in its neighborhood, which poses a challenge for its practical applica- tion. In contrast, although Multi-layer Perceptron (MLP) performs poorly, it has a shorter inference time and is more flexible in practical applications. We uti- lize a distillation model to combine the powerful inference capabilities of GNN with the inference effciency of MLP. Distillation models usually use a predefined distance function to quantify the differences between teacher-student networks, but this cannot be well applied to various complex scenarios. In addition, the limited node information severely affects the learning ability of MLP. Therefore, to cope with these problems. Firstly, we propose an Adversarial Generative Dis- criminator (AGD), which trains the discriminators and generators against each other to adaptively detect and reduce the differences. Secondly, we also propose the Feature Aggregation Module (FAM) to help the MLP obtain suffcient fea- ture information before distillation starts. In the experiments, it is shown that our approach can achieve good results in link prediction tasks, outperforming the baseline model Linkless Prediction (LLP) and maintaining a good inference speed on eight datasets in two different settings∗ . ∗The code on https://github.com/lwuen/LPVAKD.git
- 12 December 2024
- Published by Springer Nature in Research Square
Open AccessLink Prediction via Adversarial Knowledge Distillation and Feature Aggregation
Graph neural networks (GNN) have shown strong performance in link prediction tasks. However, it is susceptible to higher latency due to the trivial correlation of data in its neighborhood, which poses a challenge for its practical applica- tion. In contrast, although Multi-layer Perceptron (MLP) performs poorly, it has a shorter inference time and is more flexible in practical applications. We uti- lize a distillation model to combine the powerful inference capabilities of GNN with the inference effciency of MLP. Distillation models usually use a predefined distance function to quantify the differences between teacher-student networks, but this cannot be well applied to various complex scenarios. In addition, the limited node information severely affects the learning ability of MLP. Therefore, to cope with these problems. Firstly, we propose an Adversarial Generative Dis- criminator (AGD), which trains the discriminators and generators against each other to adaptively detect and reduce the differences. Secondly, we also propose the Feature Aggregation Module (FAM) to help the MLP obtain suffcient fea- ture information before distillation starts. In the experiments, it is shown that our approach can achieve good results in link prediction tasks, outperforming the baseline model Linkless Prediction (LLP) and maintaining a good inference speed on eight datasets in two different settings∗ . ∗The code on https://github.com/lwuen/LPVAKD.git
- 4 December 2024
- Published by Springer Nature
- p. 203-219
DRIVPocket: A Dual-stream Rotation Invariance in Feature Sampling and Voxel Fusion Approach for Protein Binding Site Prediction
- 4 December 2024
- Published by Springer Nature
- p. 203-219
DRIVPocket: A Dual-stream Rotation Invariance in Feature Sampling and Voxel Fusion Approach for Protein Binding Site Prediction
- 3 December 2024
- Published by Springer Nature
- p. 440-456
Cluster-Mined Negative Samples for Enhanced Unsupervised Sentence Representation Learning
- 3 December 2024
- Published by Springer Nature
- p. 440-456
Cluster-Mined Negative Samples for Enhanced Unsupervised Sentence Representation Learning
- 4 November 2024
- Published by Springer Nature
- p. 309-322
FedDCP: Personalized Federated Learning Based on Dual Classifiers and Prototypes
- 4 November 2024
- Published by Springer Nature
- p. 309-322
FedDCP: Personalized Federated Learning Based on Dual Classifiers and Prototypes
- 3 November 2024
- Published by Springer Nature
- p. 504-517
RRANet: A Reverse Region-Aware Network with Edge Difference for Accurate Breast Tumor Segmentation in Ultrasound Images
- 3 November 2024
- Published by Springer Nature
- p. 504-517
RRANet: A Reverse Region-Aware Network with Edge Difference for Accurate Breast Tumor Segmentation in Ultrasound Images
- 10 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 21 (6) , 2269-2279
APMG: 3D Molecule Generation Driven by Atomic Chemical Properties
Recently, mask-fill-based 3D Molecular Generation (MG) methods have become very popular in virtual drug design. However, the existing MG methods ignore the chemical properties of atoms and contain inappropriate atomic position training data, which limits their generation capability. To mitigate the above issues, this paper presents a novel mask-fill-based 3D molecule generation model driven by atomic chemical properties (APMG). Specifically, we construct a new attention-MPNN-based encoder and introduce the electronic information into atom representations to enrich chemical properties. Also, a multi-functional classifier is designed to predict the electronic information of each generated atom, guiding the type prediction of elements and bonds. By design, the proposed method uses the chemical properties of atoms and their correlations for high-quality molecule generation. Second, to optimize the atomic position training data, we propose a novel atomic training position generation approach using the Chi-Square distribution. We evaluate our APMG method on the CrossDocked dataset and visualize the docking states of the pockets and generated molecules. The obtained results demonstrate the superiority and merits of APMG over the state-of-the-art approaches. The dataset and codes will be available on the project homepage: https://github.com/JU-HuaY/APMG
- 10 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 21 (6) , 2269-2279
APMG: 3D Molecule Generation Driven by Atomic Chemical Properties
Recently, mask-fill-based 3D Molecular Generation (MG) methods have become very popular in virtual drug design. However, the existing MG methods ignore the chemical properties of atoms and contain inappropriate atomic position training data, which limits their generation capability. To mitigate the above issues, this paper presents a novel mask-fill-based 3D molecule generation model driven by atomic chemical properties (APMG). Specifically, we construct a new attention-MPNN-based encoder and introduce the electronic information into atom representations to enrich chemical properties. Also, a multi-functional classifier is designed to predict the electronic information of each generated atom, guiding the type prediction of elements and bonds. By design, the proposed method uses the chemical properties of atoms and their correlations for high-quality molecule generation. Second, to optimize the atomic position training data, we propose a novel atomic training position generation approach using the Chi-Square distribution. We evaluate our APMG method on the CrossDocked dataset and visualize the docking states of the pockets and generated molecules. The obtained results demonstrate the superiority and merits of APMG over the state-of-the-art approaches. The dataset and codes will be available on the project homepage: https://github.com/JU-HuaY/APMG
- Top Cited Papers
- 22 August 2024
- Published by Elsevier in Pattern Recognition
- Vol. 157
MMDG-DTI: Drug–target interaction prediction via multimodal feature fusion and domain generalization
- 22 August 2024
- Published by Elsevier in Pattern Recognition
- Vol. 157
Top Cited PapersMMDG-DTI: Drug–target interaction prediction via multimodal feature fusion and domain generalization