Hai Cui
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hai Cui has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Yijia Zhang
School of Information Science and Technology, Dalian Maritime University, Dalian, China
12 shared publications - Tao Peng
College of Computer Science and Technology, Jilin University, Changchun, 130012, Jilin, China; College of Software, Jilin University, Changchun, 130012, Jilin, China; Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012, Jilin, China
6 shared publications - Jiayu Han
Department of Linguistics, University of Washington, Seattle, 98195, WA, USA
5 shared publications - Meiyu Duan
College of Information Science and Technology, Dalian Maritime University, Dalian, 116026, Liaoning, China
5 shared publications - Ridong Han
School of Computer Science and Technology/School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, China; College of Computer Science and Technology, Jilin University, Changchun, 130012, Jilin, China; Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012, Jilin, China
5 shared publications - Haijia Bi
College of Computer Science and Technology, Jilin University, Changchun, 130012, Jilin, China
4 shared publications
Latest Publications
- 1 July 2026
- Published by Elsevier in Neural Networks
- Vol. 204, 109324
TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning
- 1 July 2026
- Published by Elsevier in Neural Networks
- Vol. 204, 109324
TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning
- 27 June 2026
- Published by Elsevier in Information Fusion
- Vol. 136
Collaborative cross-modal fusion network for medical report generation
- 27 June 2026
- Published by Elsevier in Information Fusion
- Vol. 136
Collaborative cross-modal fusion network for medical report generation
- 25 March 2026
- Published by Elsevier in Neural Networks
- Vol. 201, 108882
Multi-modal contrastive learning based on molecular and textual data for drug response prediction
- 25 March 2026
- Published by Elsevier in Neural Networks
- Vol. 201, 108882
Multi-modal contrastive learning based on molecular and textual data for drug response prediction
- 22 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (4) , 3208-3218
KEGCL: Knowledge-Enhanced Graph Contrastive Learning for Protein Complex Identification
Protein complexes play essential roles in cellular functions, and accurate identification of these complexes is critical for understanding biological processes and disease mechanisms. Existing methods frequently compromise the global topology of protein-protein interaction (PPI) networks when incorporating biological resources. Moreover, they fail to adequately address the intrinsic sparsity of PPI data and the widespread occurrence of false positives and false negatives. These approaches also struggle to capture the diverse neighborhood dependencies necessary to represent distinct functional roles of proteins within complexes. To address these limitations, we propose a knowledge-enhanced graph contrastive learning (KEGCL) framework for protein complex identification. KEGCL constructs a knowledge-enhanced PPI network by integrating external biological priors. A perturbation strategy guided by spatiotemporal constraints is then applied to selectively reintroduce functionally relevant interactions, thereby enhancing semantic diversity in the generated graph views. Based on this, graph convolutional encoders with randomized propagation depths are used to capture protein interaction patterns at multiple structural levels, enhancing the model's ability to represent both densely connected cores and loosely associated attachments within protein complexes. Extensive experiments on multiple real-world PPI datasets show that KEGCL achieves competitive performance compared with state-of-the-art methods, and enrichment analyses confirm the biological relevance of the identified complexes. Source code and data are available at https://github.com/quyanchen/KEGCL.
- 22 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (4) , 3208-3218
KEGCL: Knowledge-Enhanced Graph Contrastive Learning for Protein Complex Identification
Protein complexes play essential roles in cellular functions, and accurate identification of these complexes is critical for understanding biological processes and disease mechanisms. Existing methods frequently compromise the global topology of protein-protein interaction (PPI) networks when incorporating biological resources. Moreover, they fail to adequately address the intrinsic sparsity of PPI data and the widespread occurrence of false positives and false negatives. These approaches also struggle to capture the diverse neighborhood dependencies necessary to represent distinct functional roles of proteins within complexes. To address these limitations, we propose a knowledge-enhanced graph contrastive learning (KEGCL) framework for protein complex identification. KEGCL constructs a knowledge-enhanced PPI network by integrating external biological priors. A perturbation strategy guided by spatiotemporal constraints is then applied to selectively reintroduce functionally relevant interactions, thereby enhancing semantic diversity in the generated graph views. Based on this, graph convolutional encoders with randomized propagation depths are used to capture protein interaction patterns at multiple structural levels, enhancing the model's ability to represent both densely connected cores and loosely associated attachments within protein complexes. Extensive experiments on multiple real-world PPI datasets show that KEGCL achieves competitive performance compared with state-of-the-art methods, and enrichment analyses confirm the biological relevance of the identified complexes. Source code and data are available at https://github.com/quyanchen/KEGCL.
- 23 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (7) , 5530-5541
Collaborative Relation Augmentation With Hierarchical Prescription Inference for Medication Recommendation
Medication recommendation systems have emerged as crucial tools in healthcare, offering personalized and effective drug combinations tailored to individual patient's clinical profiles. However, most existing approaches primarily focus on drug prediction by analyzing patient-drug interactions, often neglecting the intricate correlations between diseases and drugs. To address above limitation, this paper proposes a novel Collaborative Relation augmentation with Hierarchical Prescription inference network (CRHP) for effective medication recommendation. CRHP first constructs multiple covariance knowledge graphs to capture fine-grained interaction relationships between different entities from a global perspective. Based on self-built knowledge graphs, CRHP designs a collaborative relation augmented learning module, which introduces hypergraph convolutional networks to capture high-order association information between different entities. Moreover, CRHP devises a hierarchical prescription inference module that formulates drug prescriptions based on both current and historical patient information. The extensive experiments on two publicly available real-world medical datasets, MIMIC-III and MIMIC-IV, demonstrate the effectiveness of CRHP. The results indicate significant performance improvements over baseline methods, with gains of 2.12 and 1.31 in Jaccard, 1.91 and 1.83 in PRAUC, and 1.79 and 0.98 in F1-score (in percentage points).
- 23 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (7) , 5530-5541
Collaborative Relation Augmentation With Hierarchical Prescription Inference for Medication Recommendation
Medication recommendation systems have emerged as crucial tools in healthcare, offering personalized and effective drug combinations tailored to individual patient's clinical profiles. However, most existing approaches primarily focus on drug prediction by analyzing patient-drug interactions, often neglecting the intricate correlations between diseases and drugs. To address above limitation, this paper proposes a novel Collaborative Relation augmentation with Hierarchical Prescription inference network (CRHP) for effective medication recommendation. CRHP first constructs multiple covariance knowledge graphs to capture fine-grained interaction relationships between different entities from a global perspective. Based on self-built knowledge graphs, CRHP designs a collaborative relation augmented learning module, which introduces hypergraph convolutional networks to capture high-order association information between different entities. Moreover, CRHP devises a hierarchical prescription inference module that formulates drug prescriptions based on both current and historical patient information. The extensive experiments on two publicly available real-world medical datasets, MIMIC-III and MIMIC-IV, demonstrate the effectiveness of CRHP. The results indicate significant performance improvements over baseline methods, with gains of 2.12 and 1.31 in Jaccard, 1.91 and 1.83 in PRAUC, and 1.79 and 0.98 in F1-score (in percentage points).
- 20 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (10) , 7704-7716
Sign-Aware Graph Contrastive Learning for Drug Repositioning
Drug repositioning, which identifies new therapeutic potential of approved drugs, is pivotal in accelerating drug discovery. Recently, growing efforts are devoted to applying graph neural networks (GNNs) for effectively modeling drug-disease associations (DDAs). However, current GNN-based methods are generally designed for unsigned graphs and fail to gain complementary insights provided by negative links. Despite the proposal of sign-aware GNNs in general fields, there exist two intractable challenges when indiscriminately deploying prior solutions into drug repositioning. (i) How to explicitly connect the nodes within the same set (disease-disease and drug-drug)? (ii) How to design the contrastive learning objective for signed graphs? To this end, we propose a novel sign-aware graph contrastive learning approach, namely SIGDR, which takes both the positive and negative links from signed biological networks into consideration to identify underlying DDAs. To handle the first challenge, we measure the drug and disease similarity and form signed unipartite graphs according to similarity scores. For the second challenge, a signed bipartite graph is then constructed from the annotated DDA dataset. Through dividing above obtained signed graphs into positive and negative subgraphs respectively, we devise the inter-view contrastive learning auxiliary task to enhance the consistency of node representations derived from partitioned subgraphs with the same link type. Extensive experiments conducted on three benchmarks under 10-fold cross-validation demonstrate the model effectiveness. Source code and datasets are available at https://github.com/OleCui/paper_SIGDR.
- 20 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (10) , 7704-7716
Sign-Aware Graph Contrastive Learning for Drug Repositioning
Drug repositioning, which identifies new therapeutic potential of approved drugs, is pivotal in accelerating drug discovery. Recently, growing efforts are devoted to applying graph neural networks (GNNs) for effectively modeling drug-disease associations (DDAs). However, current GNN-based methods are generally designed for unsigned graphs and fail to gain complementary insights provided by negative links. Despite the proposal of sign-aware GNNs in general fields, there exist two intractable challenges when indiscriminately deploying prior solutions into drug repositioning. (i) How to explicitly connect the nodes within the same set (disease-disease and drug-drug)? (ii) How to design the contrastive learning objective for signed graphs? To this end, we propose a novel sign-aware graph contrastive learning approach, namely SIGDR, which takes both the positive and negative links from signed biological networks into consideration to identify underlying DDAs. To handle the first challenge, we measure the drug and disease similarity and form signed unipartite graphs according to similarity scores. For the second challenge, a signed bipartite graph is then constructed from the annotated DDA dataset. Through dividing above obtained signed graphs into positive and negative subgraphs respectively, we devise the inter-view contrastive learning auxiliary task to enhance the consistency of node representations derived from partitioned subgraphs with the same link type. Extensive experiments conducted on three benchmarks under 10-fold cross-validation demonstrate the model effectiveness. Source code and datasets are available at https://github.com/OleCui/paper_SIGDR.
- 29 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (6) , 4525-4534
Knowledge-Driven and Relation-Aware Synergistic Learning for Drug Repositioning
As an effective and low-risk approach to identify new therapeutic pathways for existing drugs, drug repositioning has been extensively utilized to expedit drug discovery processes. However, current knowledge graph (KG)-based methodologies encounter several hurdles in this context. Firstly, most graph neural network (GNN)- based approaches fail to adequately capture the intricate relationships between drug-drug, drug-disease, or diseasedisease. Secondly, the subtle synergistic mechanisms between drugs and diseases remain underexplored. Lastly, the training of knowledge graph embedding (KGE) methods is susceptible to noise, leading to unstable model optimization. To address these challenges, we intruduce KRANE, a knowledge-driven and relation-aware synergistic learning method for drug repositioning. KRANE addresses these issues through three innovative modules. Firstly, we design a relation-aware feature extractor (RAFE), which utilizes the contextual triples attention scores in KG to effectively integrate drug-related knowledge and enhance the representation of complex relational features. Secondly, we adopt a synergistic feature reconstruction module as a decoder to extract synergistic heterogeneous feature interactions between drugs and diseases from entity and relation representations. Finally, we propose a knowledgeregulated loss function to mitigate the impact of noise on model training. Experiments conducted on three publicly available datasets demonstrate that KRANE significantly outperforms existing methods. The source code and datasets are available at https://github.com/qifen37/KRANE.
- 29 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (6) , 4525-4534
Knowledge-Driven and Relation-Aware Synergistic Learning for Drug Repositioning
As an effective and low-risk approach to identify new therapeutic pathways for existing drugs, drug repositioning has been extensively utilized to expedit drug discovery processes. However, current knowledge graph (KG)-based methodologies encounter several hurdles in this context. Firstly, most graph neural network (GNN)- based approaches fail to adequately capture the intricate relationships between drug-drug, drug-disease, or diseasedisease. Secondly, the subtle synergistic mechanisms between drugs and diseases remain underexplored. Lastly, the training of knowledge graph embedding (KGE) methods is susceptible to noise, leading to unstable model optimization. To address these challenges, we intruduce KRANE, a knowledge-driven and relation-aware synergistic learning method for drug repositioning. KRANE addresses these issues through three innovative modules. Firstly, we design a relation-aware feature extractor (RAFE), which utilizes the contextual triples attention scores in KG to effectively integrate drug-related knowledge and enhance the representation of complex relational features. Secondly, we adopt a synergistic feature reconstruction module as a decoder to extract synergistic heterogeneous feature interactions between drugs and diseases from entity and relation representations. Finally, we propose a knowledgeregulated loss function to mitigate the impact of noise on model training. Experiments conducted on three publicly available datasets demonstrate that KRANE significantly outperforms existing methods. The source code and datasets are available at https://github.com/qifen37/KRANE.
- 10 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (9) , 6902-6914
Multi-View Contrastive Learning for Drug Repositioning on Heterogeneous Biological Networks
Drug repositioning, which identifies new therapeutic potential of approved drugs, is instrumental in accelerating drug discovery. Recently, to alleviate the effect of data sparsity on predicting possible drug-disease associations (DDAs), graph contrastive learning (GCL) has emerged as a promising paradigm for learning discriminative representations of drugs and diseases through distilling informative self-supervised signals. However, existing GCLbased methods devised for DDA prediction still encounter two limitations. Firstly, the crucial heterogeneous property, which allows for capturing nuanced interaction semantics between biological entities, is overlooked. The second is how to perform contrastive view augmentation without relying on stochastic perturbation. In this study, we propose a novel multi-view contrastive learning approach for DDA prediction, namely MICLE. To handle the first issue, proteinrelated bipartite graphs are integrated with the original DDA network in advance, thereby composing a heterogeneous biological network (HBN). Besides, heterogeneous graph neural network is applied to mine the rich connectivity patterns implicit in the above HBN. For the second limitation, we design the complementary inter-view and intra-view contrastive learning tasks. Specifically, the former ensures that the mutual information between paired nodes across views is maximized, the latter enhances the agreement between each node and its first-order neighbors on similarity networks. Extensive experiments conducted on three benchmarks under 10-fold cross-validation demonstrate the model effectiveness. Source code and datasets are available at https://github.com/OleCui/paper MICLE.
- 10 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (9) , 6902-6914
Multi-View Contrastive Learning for Drug Repositioning on Heterogeneous Biological Networks
Drug repositioning, which identifies new therapeutic potential of approved drugs, is instrumental in accelerating drug discovery. Recently, to alleviate the effect of data sparsity on predicting possible drug-disease associations (DDAs), graph contrastive learning (GCL) has emerged as a promising paradigm for learning discriminative representations of drugs and diseases through distilling informative self-supervised signals. However, existing GCLbased methods devised for DDA prediction still encounter two limitations. Firstly, the crucial heterogeneous property, which allows for capturing nuanced interaction semantics between biological entities, is overlooked. The second is how to perform contrastive view augmentation without relying on stochastic perturbation. In this study, we propose a novel multi-view contrastive learning approach for DDA prediction, namely MICLE. To handle the first issue, proteinrelated bipartite graphs are integrated with the original DDA network in advance, thereby composing a heterogeneous biological network (HBN). Besides, heterogeneous graph neural network is applied to mine the rich connectivity patterns implicit in the above HBN. For the second limitation, we design the complementary inter-view and intra-view contrastive learning tasks. Specifically, the former ensures that the mutual information between paired nodes across views is maximized, the latter enhances the agreement between each node and its first-order neighbors on similarity networks. Extensive experiments conducted on three benchmarks under 10-fold cross-validation demonstrate the model effectiveness. Source code and datasets are available at https://github.com/OleCui/paper MICLE.
- 9 April 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 280
Manifold knowledge-guided feature fusion network for multimodal sentiment analysis
- 9 April 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 280
Manifold knowledge-guided feature fusion network for multimodal sentiment analysis
- 19 December 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 309
Dynamic matching-prototypical learning for noisy few-shot relation classification
- 19 December 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 309
Dynamic matching-prototypical learning for noisy few-shot relation classification