Haijia Bi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Haijia Bi has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Hai Cui
Information Science and Technology College, Dalian Maritime University, Dalian, China
4 shared publications - Lu Liu
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
4 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
4 shared publications - Meiyu Duan
College of Information Science and Technology, Dalian Maritime University, Dalian, 116026, Liaoning, China
3 shared publications - Yijia Zhang
School of Information Science and Technology, Dalian Maritime University, Dalian, China
3 shared publications - Jiayu Han
Department of Linguistics, University of Washington, Seattle, 98195, WA, USA
2 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
- 12 December 2025
- Published by Elsevier in Neural Networks
- Vol. 197, 108469
Document-level relation extraction with entity type constraints
- 12 December 2025
- Published by Elsevier in Neural Networks
- Vol. 197, 108469
Document-level relation extraction with entity type constraints
- 16 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 332
Rethinking structural semantics for unsupervised graph domain adaptation
- 16 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 332
Rethinking structural semantics for unsupervised graph domain adaptation
- 31 July 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 183
Dynamic Lightweight Siamese-Prototypical network for few-shot relation classification
- 31 July 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 183
Dynamic Lightweight Siamese-Prototypical network for few-shot relation classification
- 17 July 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 296
Fine-Grained Graph Domain Adaptation via Instance Contrastive Learning
- 17 July 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 296
Fine-Grained Graph Domain Adaptation via Instance Contrastive Learning
- 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.
- 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
- Open Access
- 22 November 2024
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (1)
Heterogeneous graph contrastive learning with gradient balance for drug repositioning
Drug repositioning, which involves identifying new therapeutic indications for approved drugs, is pivotal in accelerating drug discovery. Recently, to mitigate the effect of label sparsity on inferring potential drug–disease associations (DDAs), graph contrastive learning (GCL) has emerged as a promising paradigm to supplement high-quality self-supervised signals through designing auxiliary tasks, then transfer shareable knowledge to main task, i.e. DDA prediction. However, existing approaches still encounter two limitations. The first is how to generate augmented views for fully capturing higher-order interaction semantics. The second is the optimization imbalance issue between auxiliary and main tasks. In this paper, we propose a novel heterogeneous Graph Contrastive learning method with Gradient Balance for DDA prediction, namely GCGB. To handle the first challenge, a fusion view is introduced to integrate both semantic views (drug and disease similarity networks) and interaction view (heterogeneous biomedical network). Next, inter-view contrastive learning auxiliary tasks are designed to contrast the fusion view with semantic and interaction views, respectively. For the second challenge, we adaptively adjust the gradient of GCL auxiliary tasks from the perspective of gradient direction and magnitude for better guiding parameter update toward main task. Extensive experiments conducted on three benchmarks under 10-fold cross-validation demonstrate the model effectiveness.
- 22 November 2024
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (1)
Open AccessHeterogeneous graph contrastive learning with gradient balance for drug repositioning
Drug repositioning, which involves identifying new therapeutic indications for approved drugs, is pivotal in accelerating drug discovery. Recently, to mitigate the effect of label sparsity on inferring potential drug–disease associations (DDAs), graph contrastive learning (GCL) has emerged as a promising paradigm to supplement high-quality self-supervised signals through designing auxiliary tasks, then transfer shareable knowledge to main task, i.e. DDA prediction. However, existing approaches still encounter two limitations. The first is how to generate augmented views for fully capturing higher-order interaction semantics. The second is the optimization imbalance issue between auxiliary and main tasks. In this paper, we propose a novel heterogeneous Graph Contrastive learning method with Gradient Balance for DDA prediction, namely GCGB. To handle the first challenge, a fusion view is introduced to integrate both semantic views (drug and disease similarity networks) and interaction view (heterogeneous biomedical network). Next, inter-view contrastive learning auxiliary tasks are designed to contrast the fusion view with semantic and interaction views, respectively. For the second challenge, we adaptively adjust the gradient of GCL auxiliary tasks from the perspective of gradient direction and magnitude for better guiding parameter update toward main task. Extensive experiments conducted on three benchmarks under 10-fold cross-validation demonstrate the model effectiveness.