Xuan Zang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Xuan Zang has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Buzhou Tang
School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China
7 shared publications - Junjie Zhang
School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, 518055, Guangdong, China
4 shared publications - Bo Yang
Jilin University
2 shared publications - Anchen Li
Department of Computer Science, Aalto University, Espoo, Finland
1 shared publication Hao Chen
School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China
1 shared publication- Hechang Chen
School of Artificial Intelligence, Jilin University, Changchun, China
1 shared publication
Latest Publications
- 15 July 2025
- Published by Elsevier in Information Fusion
- Vol. 125
Molecular representation learning via multimodal fusion and decoupling
- 15 July 2025
- Published by Elsevier in Information Fusion
- Vol. 125
Molecular representation learning via multimodal fusion and decoupling
- 14 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (1) , 700-710
Self-Supervised Molecular Representation Learning With Topology and Geometry
Molecular representation learning is of great importance for drug molecular analysis. The development in molecular representation learning has demonstrated great promise through self-supervised pre-training strategy to overcome the scarcity of labeled molecular property data. Recent studies concentrate on pre-training molecular representation encoders by integrating both 2D topological and 3D geometric structures. However, existing methods rely on molecule-level or atom-level alignment for different views, while overlooking hierarchical self-supervised learning to capture both inter-molecule and intra-molecule correlation. Additionally, most methods employ 2D or 3D encoders to individually extract molecular characteristics locally or globally for molecular property prediction. The potential for effectively fusing these two molecular representations remains to be explored. In this work, we propose a M ulti- V iew M olecular R epresentation L earning method (MVMRL) for molecular property prediction. First, hierarchical pre-training pretext tasks are designed, including fine-grained atom-level tasks for 2D molecular graphs as well as coarse-grained molecule-level tasks for 3D molecular graphs to provide complementary information to each other. Subsequently, a motif-level fusion pattern of multi-view molecular representations is presented during fine-tuning to enhance the performance of molecular property prediction. We evaluate the effectiveness of the proposed MVMRL by comparing with state-of-the-art baselines on molecular property prediction tasks, and the experimental results demonstrate the superiority of MVMRL.
- 14 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (1) , 700-710
Self-Supervised Molecular Representation Learning With Topology and Geometry
Molecular representation learning is of great importance for drug molecular analysis. The development in molecular representation learning has demonstrated great promise through self-supervised pre-training strategy to overcome the scarcity of labeled molecular property data. Recent studies concentrate on pre-training molecular representation encoders by integrating both 2D topological and 3D geometric structures. However, existing methods rely on molecule-level or atom-level alignment for different views, while overlooking hierarchical self-supervised learning to capture both inter-molecule and intra-molecule correlation. Additionally, most methods employ 2D or 3D encoders to individually extract molecular characteristics locally or globally for molecular property prediction. The potential for effectively fusing these two molecular representations remains to be explored. In this work, we propose a M ulti- V iew M olecular R epresentation L earning method (MVMRL) for molecular property prediction. First, hierarchical pre-training pretext tasks are designed, including fine-grained atom-level tasks for 2D molecular graphs as well as coarse-grained molecule-level tasks for 3D molecular graphs to provide complementary information to each other. Subsequently, a motif-level fusion pattern of multi-view molecular representations is presented during fine-tuning to enhance the performance of molecular property prediction. We evaluate the effectiveness of the proposed MVMRL by comparing with state-of-the-art baselines on molecular property prediction tasks, and the experimental results demonstrate the superiority of MVMRL.
- 30 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (2) , 1525-1533
Revisiting Drug Recommendation From a Causal Perspective
Drug recommendation that aims to provide a prescription for a patient is an essential task in healthcare. Drug molecular graphs provide valuable support for drug recommendation. Existing methods tend to overlook drugs' molecular graphs or use the core substructures of molecular graphs with a rule-based segmentation strategy. However, such methods have several limitations: (1) The rule-based segmentation strategy is inflexible and sub-optimal for extremely complex scenarios. (2) The core substructures derived only consider the drug's chemical characteristics and ignore the patient's health condition. (3) The spurious correlation brought by trivial substructures is disregarded. To address these limitations, we design a novel drug recommendation method from a causal perspective, where a conditional causal representation learner for drug recommendation is proposed. Specifically, we first separate the drug molecular representation into causal and spurious parts depending on various patients' health conditions. Then, we eliminate the spurious correlation caused by the spurious part with causal intervention. Extensive experiments on the MIMIC-III and MIMIC-IV datasets demonstrate that our approach achieves new state-of-the-art performance (e.g., 6.68% Jaccard improvements on MIMIC-III with p-value $\ll$ 0.05). Source codes are available at https://github.com/junjzhang7/CRec .
- 30 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (2) , 1525-1533
Revisiting Drug Recommendation From a Causal Perspective
Drug recommendation that aims to provide a prescription for a patient is an essential task in healthcare. Drug molecular graphs provide valuable support for drug recommendation. Existing methods tend to overlook drugs' molecular graphs or use the core substructures of molecular graphs with a rule-based segmentation strategy. However, such methods have several limitations: (1) The rule-based segmentation strategy is inflexible and sub-optimal for extremely complex scenarios. (2) The core substructures derived only consider the drug's chemical characteristics and ignore the patient's health condition. (3) The spurious correlation brought by trivial substructures is disregarded. To address these limitations, we design a novel drug recommendation method from a causal perspective, where a conditional causal representation learner for drug recommendation is proposed. Specifically, we first separate the drug molecular representation into causal and spurious parts depending on various patients' health conditions. Then, we eliminate the spurious correlation caused by the spurious part with causal intervention. Extensive experiments on the MIMIC-III and MIMIC-IV datasets demonstrate that our approach achieves new state-of-the-art performance (e.g., 6.68% Jaccard improvements on MIMIC-III with p-value $\ll$ 0.05). Source codes are available at https://github.com/junjzhang7/CRec .
- 3 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (12) , 7659-7669
Self-Supervised Pre-Training via Multi-View Graph Information Bottleneck for Molecular Property Prediction
Molecular representation learning has remarkably accelerated the development of drug analysis and discovery. It implements machine learning methods to encode molecule embeddings for diverse downstream drug-related tasks. Due to the scarcity of labeled molecular data, self-supervised molecular pre-training is promising as it can handle large-scale unlabeled molecular data to prompt representation learning. Although many universal graph pre-training methods have been successfully introduced into molecular learning, there still exist some limitations. Many graph augmentation methods, such as atom deletion and bond perturbation, tend to destroy the intrinsic properties and connections of molecules. In addition, identifying subgraphs that are important to specific chemical properties is also challenging for molecular learning. To address these limitations, we propose the self-supervised Molecular Graph Information Bottleneck (MGIB) model for molecular pre-training. MGIB observes molecular graphs from the atom view and the motif view, deploys a learnable graph compression process to extract the core subgraphs, and extends the graph information bottleneck into the self-supervised molecular pre-training framework. Model analysis validates the contribution of the self-supervised graph information bottleneck and illustrates the interpretability of MGIB through the extracted subgraphs. Extensive experiments involving molecular property prediction, including 7 binary classification tasks and 6 regression tasks demonstrate the effectiveness and superiority of our proposed MGIB.
- 3 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (12) , 7659-7669
Self-Supervised Pre-Training via Multi-View Graph Information Bottleneck for Molecular Property Prediction
Molecular representation learning has remarkably accelerated the development of drug analysis and discovery. It implements machine learning methods to encode molecule embeddings for diverse downstream drug-related tasks. Due to the scarcity of labeled molecular data, self-supervised molecular pre-training is promising as it can handle large-scale unlabeled molecular data to prompt representation learning. Although many universal graph pre-training methods have been successfully introduced into molecular learning, there still exist some limitations. Many graph augmentation methods, such as atom deletion and bond perturbation, tend to destroy the intrinsic properties and connections of molecules. In addition, identifying subgraphs that are important to specific chemical properties is also challenging for molecular learning. To address these limitations, we propose the self-supervised Molecular Graph Information Bottleneck (MGIB) model for molecular pre-training. MGIB observes molecular graphs from the atom view and the motif view, deploys a learnable graph compression process to extract the core subgraphs, and extends the graph information bottleneck into the self-supervised molecular pre-training framework. Model analysis validates the contribution of the self-supervised graph information bottleneck and illustrates the interpretability of MGIB through the extracted subgraphs. Extensive experiments involving molecular property prediction, including 7 binary classification tasks and 6 regression tasks demonstrate the effectiveness and superiority of our proposed MGIB.
- 10 May 2023
- Published by Elsevier in Expert Systems with Applications
- Vol. 228
Self-supervised Dynamic Graph Embedding with evolutionary neighborhood and community
- 10 May 2023
- Published by Elsevier in Expert Systems with Applications
- Vol. 228
Self-supervised Dynamic Graph Embedding with evolutionary neighborhood and community
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1714-1722
TMMDA: A New Token Mixup Multimodal Data Augmentation for Multimodal Sentiment Analysis
Existing methods for Multimodal Sentiment Analysis (MSA) mainly focus on integrating multimodal data effectively on limited multimodal data. Learning more informative multimodal representation often relies on large-scale labeled datasets, which are difficult and unrealistic to obtain. To learn informative multimodal representation on limited labeled datasets as more as possible, we proposed TMMDA for MSA, a new Token Mixup Multimodal Data Augmentation, which first generates new virtual modalities from the mixed token-level representation of raw modalities, and then enhances the representation of raw modalities by utilizing the representation of the generated virtual modalities. To preserve semantics during virtual modality generation, we propose a novel cross-modal token mixup strategy based on the generative adversarial network. Extensive experiments on two benchmark datasets, i.e., CMU-MOSI and CMU-MOSEI, verify the superiority of our model compared with several state-of-the-art baselines. The code is available at https://github.com/xiaobaicaihhh/TMMDA.
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1714-1722
Open AccessTMMDA: A New Token Mixup Multimodal Data Augmentation for Multimodal Sentiment Analysis
Existing methods for Multimodal Sentiment Analysis (MSA) mainly focus on integrating multimodal data effectively on limited multimodal data. Learning more informative multimodal representation often relies on large-scale labeled datasets, which are difficult and unrealistic to obtain. To learn informative multimodal representation on limited labeled datasets as more as possible, we proposed TMMDA for MSA, a new Token Mixup Multimodal Data Augmentation, which first generates new virtual modalities from the mixed token-level representation of raw modalities, and then enhances the representation of raw modalities by utilizing the representation of the generated virtual modalities. To preserve semantics during virtual modality generation, we propose a novel cross-modal token mixup strategy based on the generative adversarial network. Extensive experiments on two benchmark datasets, i.e., CMU-MOSI and CMU-MOSEI, verify the superiority of our model compared with several state-of-the-art baselines. The code is available at https://github.com/xiaobaicaihhh/TMMDA.
- Top Cited PapersOpen Access
- 17 February 2023
- Published by Springer Nature in Communications Chemistry
- Vol. 6 (1) , 1-10
Hierarchical Molecular Graph Self-Supervised Learning for property prediction
Molecular graph representation learning has shown considerable strength in molecular analysis and drug discovery. Due to the difficulty of obtaining molecular property labels, pre-training models based on self-supervised learning has become increasingly popular in molecular representation learning. Notably, Graph Neural Networks (GNN) are employed as the backbones to encode implicit representations of molecules in most existing works. However, vanilla GNN encoders ignore chemical structural information and functions implied in molecular motifs, and obtaining the graph-level representation via the READOUT function hinders the interaction of graph and node representations. In this paper, we propose Hierarchical Molecular Graph Self-supervised Learning (HiMol), which introduces a pre-training framework to learn molecule representation for property prediction. First, we present a Hierarchical Molecular Graph Neural Network (HMGNN), which encodes motif structure and extracts node-motif-graph hierarchical molecular representations. Then, we introduce Multi-level Self-supervised Pre-training (MSP), in which corresponding multi-level generative and predictive tasks are designed as self-supervised signals of HiMol model. Finally, superior molecular property prediction results on both classification and regression tasks demonstrate the effectiveness of HiMol. Moreover, the visualization performance in the downstream dataset shows that the molecule representations learned by HiMol can capture chemical semantic information and properties.
- 17 February 2023
- Published by Springer Nature in Communications Chemistry
- Vol. 6 (1) , 1-10
Top Cited PapersOpen AccessHierarchical Molecular Graph Self-Supervised Learning for property prediction
Molecular graph representation learning has shown considerable strength in molecular analysis and drug discovery. Due to the difficulty of obtaining molecular property labels, pre-training models based on self-supervised learning has become increasingly popular in molecular representation learning. Notably, Graph Neural Networks (GNN) are employed as the backbones to encode implicit representations of molecules in most existing works. However, vanilla GNN encoders ignore chemical structural information and functions implied in molecular motifs, and obtaining the graph-level representation via the READOUT function hinders the interaction of graph and node representations. In this paper, we propose Hierarchical Molecular Graph Self-supervised Learning (HiMol), which introduces a pre-training framework to learn molecule representation for property prediction. First, we present a Hierarchical Molecular Graph Neural Network (HMGNN), which encodes motif structure and extracts node-motif-graph hierarchical molecular representations. Then, we introduce Multi-level Self-supervised Pre-training (MSP), in which corresponding multi-level generative and predictive tasks are designed as self-supervised signals of HiMol model. Finally, superior molecular property prediction results on both classification and regression tasks demonstrate the effectiveness of HiMol. Moreover, the visualization performance in the downstream dataset shows that the molecule representations learned by HiMol can capture chemical semantic information and properties.
- 7 August 2021
- Published by Springer Nature
- p. 236-248
DNEA: Dynamic Network Embedding Method for Anomaly Detection
- 7 August 2021
- Published by Springer Nature
- p. 236-248
DNEA: Dynamic Network Embedding Method for Anomaly Detection
- Open Access
- 16 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 185687-185697
Constrained Consistency Modeling for Attributed Network Embedding
Network embedding has emerged as a fundamental approach to network analysis tasks. Its main purpose is to learn a suitable mapping function to convert nodes in networks into a low-dimensional representations. The majority of existing studies concentrate solely on network topology structure. However, nodes are commonly associated with sufficient attribute information in real-world networks. Therefore, network embedding combining network topology structure and attribute information could be promisingly beneficial. Given this, we propose a novel attributed network embedding method called Consistency Constrained Attributed Network Embedding (CCANE), which preserves more complete information for nodes when learning the embedding representations. On the basis of the consistency of topology structure and node attributes, the CCANE is capable of learning the structure embeddings and attribute embeddings of nodes simultaneously, and then concatenate them to obtain the integrated vector representations. Moreover, the CCANE is scalable of dealing with large-scale of networks by decomposing the complicated optimization process into multiple sub-tasks in parallel. Experimental results testify the feasibility and superiority of the CCANE compared to the state-of-the-arts.
- 16 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 185687-185697
Open AccessConstrained Consistency Modeling for Attributed Network Embedding
Network embedding has emerged as a fundamental approach to network analysis tasks. Its main purpose is to learn a suitable mapping function to convert nodes in networks into a low-dimensional representations. The majority of existing studies concentrate solely on network topology structure. However, nodes are commonly associated with sufficient attribute information in real-world networks. Therefore, network embedding combining network topology structure and attribute information could be promisingly beneficial. Given this, we propose a novel attributed network embedding method called Consistency Constrained Attributed Network Embedding (CCANE), which preserves more complete information for nodes when learning the embedding representations. On the basis of the consistency of topology structure and node attributes, the CCANE is capable of learning the structure embeddings and attribute embeddings of nodes simultaneously, and then concatenate them to obtain the integrated vector representations. Moreover, the CCANE is scalable of dealing with large-scale of networks by decomposing the complicated optimization process into multiple sub-tasks in parallel. Experimental results testify the feasibility and superiority of the CCANE compared to the state-of-the-arts.