Yuan Jiang
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
Yuan Jiang has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Albert Wing Nang Leung
School of Graduate Studies, Lingnan University, Tuen Mun, Hong Kong SAR, China
1 shared publication - Chuanshan Xu
Guangzhou Municipal and Guangdong Provincial Key Laboratory of Molecular Target & Clinical Pharmacology, the NMPA and State Key Laboratory of Respiratory Disease, School of Pharmaceutical Sciences, Guangzhou Medical University, Guangzhou 511436, China
1 shared publication - Houhe Liu
Key Laboratory of Molecular Target & Clinical Pharmacology and the State & National Medical Products Administration Key Laboratory of Respiratory Disease, School of Pharmaceutical Sciences, The Fifth Affiliated Hospital, Guangzhou Medical University, Guangzhou, China
1 shared publication - Huanhuan Guo
Euler Technology, Beijing, China
1 shared publication Jiwen Yao
Key Laboratory of Molecular Target and Clinical Pharmacology, State Key Laboratory of Respiratory Disease, School of Pharmaceutical Science & Fifth Affiliated Hospital, Guangzhou Medical University, Guangzhou, China
1 shared publicationMei Lin
Key Laboratory of Molecular Target and Clinical Pharmacology, State Key Laboratory of Respiratory Disease, School of Pharmaceutical Science & Fifth Affiliated Hospital, Guangzhou Medical University, Guangzhou, China
1 shared publication
Latest Publications
- Open Access
- 30 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (1) , 1-21
Interpreting Deep Forest through Feature Contribution and MDI Feature Importance
Deep forest is a non-differentiable deep model that has achieved impressive empirical success across a wide variety of applications, especially on categorical/symbolic or mixed modeling tasks. Many of the application fields prefer explainable models, such as random forests with feature contributions that can provide a local explanation for each prediction, and Mean Decrease Impurity (MDI) that can provide global feature importance. However, deep forest, as a cascade of random forests, possesses interpretability only at the first layer. From the second layer on, many of the tree splits occur on the new features generated by the previous layer, which makes existing explaining tools for random forests inapplicable. To disclose the impact of the original features in the deep layers, we design a calculation method with an estimation step followed by a calibration step for each layer, and propose our feature contribution and MDI feature importance calculation tools for deep forest. Experimental results on both simulated data and real-world data verify the effectiveness of our methods.
- 30 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (1) , 1-21
Open AccessInterpreting Deep Forest through Feature Contribution and MDI Feature Importance
Deep forest is a non-differentiable deep model that has achieved impressive empirical success across a wide variety of applications, especially on categorical/symbolic or mixed modeling tasks. Many of the application fields prefer explainable models, such as random forests with feature contributions that can provide a local explanation for each prediction, and Mean Decrease Impurity (MDI) that can provide global feature importance. However, deep forest, as a cascade of random forests, possesses interpretability only at the first layer. From the second layer on, many of the tree splits occur on the new features generated by the previous layer, which makes existing explaining tools for random forests inapplicable. To disclose the impact of the original features in the deep layers, we design a calculation method with an estimation step followed by a calibration step for each layer, and propose our feature contribution and MDI feature importance calculation tools for deep forest. Experimental results on both simulated data and real-world data verify the effectiveness of our methods.
- Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1161-1172
Adapting to Generalized Online Label Shift by Invariant Representation Learning
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1161-1172
Open AccessAdapting to Generalized Online Label Shift by Invariant Representation Learning
- Open Access
- 29 September 2020
- Published by Frontiers Media SA in Frontiers in Chemistry
- Vol. 8, 758
Tumor Microenvironment-Responsive Nanomaterials as Targeted Delivery Carriers for Photodynamic Anticancer Therapy
Photodynamic therapy (PDT), as an alternative approach to treat tumors through reactive oxygen species (ROS) produced by the activated photosensitizers (PS) upon light irradiation, has attracted wide attention in recent years due to its low invasive and highly efficient features. However, the low hydrophilicity and poor targeting of PS limits the clinical application of PDT. Stimuli-responsive nanomaterials represent a major class of remarkable functional nanocarriers for drug delivery. In particular, tumor microenvironment-responsive nanomaterials (TMRNs) can respond to the special pathological microenvironment in tumor tissues to release the loaded drugs, that allows them to control the release of PS within tumor tissues. Recent studies have demonstrated that TMRNs can achieve the targeted release of PS at tumor sites, increase the concentration of PS in tumor tissues, and reduce side effects of PDT. Hence, in the present paper, we review TMRNs, mainly including pH-, redox-, enzymes-, and hypoxia-responsive smart nanomaterials, and focus on the application of these smart nanomaterials as targeted delivery carriers of PS in photodynamic anticancer therapy, to further boost the development of PDT in tumor therapy.
- 29 September 2020
- Published by Frontiers Media SA in Frontiers in Chemistry
- Vol. 8, 758
Open AccessTumor Microenvironment-Responsive Nanomaterials as Targeted Delivery Carriers for Photodynamic Anticancer Therapy
Photodynamic therapy (PDT), as an alternative approach to treat tumors through reactive oxygen species (ROS) produced by the activated photosensitizers (PS) upon light irradiation, has attracted wide attention in recent years due to its low invasive and highly efficient features. However, the low hydrophilicity and poor targeting of PS limits the clinical application of PDT. Stimuli-responsive nanomaterials represent a major class of remarkable functional nanocarriers for drug delivery. In particular, tumor microenvironment-responsive nanomaterials (TMRNs) can respond to the special pathological microenvironment in tumor tissues to release the loaded drugs, that allows them to control the release of PS within tumor tissues. Recent studies have demonstrated that TMRNs can achieve the targeted release of PS at tumor sites, increase the concentration of PS in tumor tissues, and reduce side effects of PDT. Hence, in the present paper, we review TMRNs, mainly including pH-, redox-, enzymes-, and hypoxia-responsive smart nanomaterials, and focus on the application of these smart nanomaterials as targeted delivery carriers of PS in photodynamic anticancer therapy, to further boost the development of PDT in tumor therapy.