Zan Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zan Zhang has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Xindong Wu
Hefei University of Technology
12 shared publications - Lei Li
Hefei University of Technology
7 shared publications - Jiuyong Li
Adelaide University
6 shared publications - Lin Liu
Adelaide University
6 shared publications - Gongqing Wu
Hefei University of Technology
5 shared publications - Xingrui Zhuo
Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology), Ministry of Education, Hefei, China
4 shared publications
Latest Publications
- 13 May 2026
- Published by Elsevier in Information Sciences
- Vol. 753
Partial multi-label learning via feature manifold learning
- 13 May 2026
- Published by Elsevier in Information Sciences
- Vol. 753
Partial multi-label learning via feature manifold learning
- 26 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (6) , 3569-3582
Exploiting Global Information for Partial Multi-Label Learning
Partial Multi-Label Learning (PML) is an emerging weakly supervised learning framework, where each instance contains a candidate label set with only some labels being ground-truth labels. Many existing PML methods recover the information of the ground-truth label set through k-Nearest Neighbor (kNN) disambiguation. However, this popular strategy might be suboptimal, as it makes disambiguation for a given instance based solely on its neighbors’ features and class labels, i.e., the local structural information in the feature space, thereby missing the opportunity to explicitly and sufficiently leverage the global structural information in the feature space to facilitate disambiguation. In this paper, we propose a novel algorithm called PRAG, i.e., PaRtiAl multi-label learning by exploiting Global information, which incorporates the global factor obtained from the features of all the training instances into the kNN disambiguation process. Specifically, we learn for each instance a global factor vector, which captures the global affinity between an instance and each label across the feature space. This global factor vector is continuously updated through iterative propagation, with each iteration computing the global factor vector based on the similarity between the instance’s features and a dynamically constructed label prototype for each label. The label prototype is formed by aggregating the features of all training instances weighted by their current estimated confidence for that label. Crucially, the global factor vector serves as a weighting mechanism during aggregation of the neighbor labels in the kNN disambiguation step. It effectively injects global structural information into the local disambiguation process, providing a more robust estimation of label confidence by mitigating the limitations of relying solely on potentially noisy local neighbors. Based on the estimated label confidence, PRAG then exploits label correlations to classify instances. We conducted extensive experiments on various real and synthetic datasets, and the results show the superiority of PRAG compared to the state-of-the-art methods.
- 26 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (6) , 3569-3582
Exploiting Global Information for Partial Multi-Label Learning
Partial Multi-Label Learning (PML) is an emerging weakly supervised learning framework, where each instance contains a candidate label set with only some labels being ground-truth labels. Many existing PML methods recover the information of the ground-truth label set through k-Nearest Neighbor (kNN) disambiguation. However, this popular strategy might be suboptimal, as it makes disambiguation for a given instance based solely on its neighbors’ features and class labels, i.e., the local structural information in the feature space, thereby missing the opportunity to explicitly and sufficiently leverage the global structural information in the feature space to facilitate disambiguation. In this paper, we propose a novel algorithm called PRAG, i.e., PaRtiAl multi-label learning by exploiting Global information, which incorporates the global factor obtained from the features of all the training instances into the kNN disambiguation process. Specifically, we learn for each instance a global factor vector, which captures the global affinity between an instance and each label across the feature space. This global factor vector is continuously updated through iterative propagation, with each iteration computing the global factor vector based on the similarity between the instance’s features and a dynamically constructed label prototype for each label. The label prototype is formed by aggregating the features of all training instances weighted by their current estimated confidence for that label. Crucially, the global factor vector serves as a weighting mechanism during aggregation of the neighbor labels in the kNN disambiguation step. It effectively injects global structural information into the local disambiguation process, providing a more robust estimation of label confidence by mitigating the limitations of relying solely on potentially noisy local neighbors. Based on the estimated label confidence, PRAG then exploits label correlations to classify instances. We conducted extensive experiments on various real and synthetic datasets, and the results show the superiority of PRAG compared to the state-of-the-art methods.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 14312-14323
Partial Multi-Label Learning via Competitive Disambiguation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 14312-14323
Partial Multi-Label Learning via Competitive Disambiguation
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 4, 3716-3724
Progressive Prefix-Memory Tuning for Complex Logical Query Answering on Knowledge Graphs
Conducting complex logical queries over knowledge graphs remains a significant challenge. Recent research has successfully leveraged Pre-trained Language Models (PLMs) to tackle Knowledge Graph Complex Query Answering (KGCQA) tasks, which is attributed to PLMs' ability to comprehend logical semantics of queries through context learning. However, existing PLM-based KGCQA methods usually overlook the harm of disordered syntax or fragmented contexts within a serialized query, posing the problem of “impossible language” to limit PLMs in grasping the logical semantics. To address this problem, we propose a Progressive Prefix-Memory Tuning (PPMT) framework for KGCQA tasks, which effectively rectifies erroneous segments in serialized queries to assist PLMs in query answering. First, we propose a prefix-memory rectification mechanism embedded in a PLM module. This mechanism assigns rectification parameters in memory stores to polish the language segments of entities, relations, and queries through specific prefixes. To further capture the logical semantics in queries, we design a progressive fine-tuning strategy, which optimizes our model through a conditional gradient update process guided by knowledge translation constraints. Extensive experiments on widely used KGCQA benchmarks demonstrate the significant superiority of PPMT in terms of HR@3 and MRR. Our codes are available at https://github.com/lazyloafer/PPMT.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 4, 3716-3724
Open AccessProgressive Prefix-Memory Tuning for Complex Logical Query Answering on Knowledge Graphs
Conducting complex logical queries over knowledge graphs remains a significant challenge. Recent research has successfully leveraged Pre-trained Language Models (PLMs) to tackle Knowledge Graph Complex Query Answering (KGCQA) tasks, which is attributed to PLMs' ability to comprehend logical semantics of queries through context learning. However, existing PLM-based KGCQA methods usually overlook the harm of disordered syntax or fragmented contexts within a serialized query, posing the problem of “impossible language” to limit PLMs in grasping the logical semantics. To address this problem, we propose a Progressive Prefix-Memory Tuning (PPMT) framework for KGCQA tasks, which effectively rectifies erroneous segments in serialized queries to assist PLMs in query answering. First, we propose a prefix-memory rectification mechanism embedded in a PLM module. This mechanism assigns rectification parameters in memory stores to polish the language segments of entities, relations, and queries through specific prefixes. To further capture the logical semantics in queries, we design a progressive fine-tuning strategy, which optimizes our model through a conditional gradient update process guided by knowledge translation constraints. Extensive experiments on widely used KGCQA benchmarks demonstrate the significant superiority of PPMT in terms of HR@3 and MRR. Our codes are available at https://github.com/lazyloafer/PPMT.
- 28 August 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Learning label-specific features for multi-dimensional classification
- 28 August 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Learning label-specific features for multi-dimensional classification
- 28 August 2025
- Published by Springer Nature
- p. 442-455
Multi-dimensional Classification Using Correlation Information
- 28 August 2025
- Published by Springer Nature
- p. 442-455
Multi-dimensional Classification Using Correlation Information
- 23 June 2025
- Published by Elsevier in Pattern Recognition
- Vol. 170
Learning embedded label-specific features for partial multi-label learning
- 23 June 2025
- Published by Elsevier in Pattern Recognition
- Vol. 170
Learning embedded label-specific features for partial multi-label learning
- 13 December 2024
- Published by Springer Nature
- p. 97-111
Multi-dimensional Classification via Global and Local Label Correlation
- 13 December 2024
- Published by Springer Nature
- p. 97-111
Multi-dimensional Classification via Global and Local Label Correlation
- 6 April 2024
- Published by Springer Nature
- p. 16-31
Dynamic Parameter Estimation for Mixtures of Plackett-Luce Models
- 6 April 2024
- Published by Springer Nature
- p. 16-31
Dynamic Parameter Estimation for Mixtures of Plackett-Luce Models
- 13 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (8) , 4178-4191
Partial Label Feature Selection: An Adaptive Approach
As an emerging weakly supervised learning framework, partial label learning aims to induce a multi-class classifier from ambiguous supervision information where each training example is associated with a set of candidate labels, among which only one is the true label. Traditional feature selection methods, either for single label and multiple label problems, are not applicable to partial label learning as the ambiguous information contained in the label space obfuscates the importance of features and misleads the selection process. This makes the selection of a proper feature subset from partial label examples particularly challenging, and therefore has rarely been investigated. In this paper, we propose a novel feature selection algorithm for partial label learning, named PLFS, which considers not only the relationships between features and labels, but also exploits the relationships between instances to select the most informative and important features to enhance the performance of partial label learning. PLFS constructs an adaptive weighted graph to exploit the similarity information among instances, differentiate the label space and weight the feature space, which leads to the selection of a proper feature subset. Extensive experiments over a broad range of benchmark data sets clearly validate the effectiveness of our proposed feature selection approach.
- 13 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (8) , 4178-4191
Partial Label Feature Selection: An Adaptive Approach
As an emerging weakly supervised learning framework, partial label learning aims to induce a multi-class classifier from ambiguous supervision information where each training example is associated with a set of candidate labels, among which only one is the true label. Traditional feature selection methods, either for single label and multiple label problems, are not applicable to partial label learning as the ambiguous information contained in the label space obfuscates the importance of features and misleads the selection process. This makes the selection of a proper feature subset from partial label examples particularly challenging, and therefore has rarely been investigated. In this paper, we propose a novel feature selection algorithm for partial label learning, named PLFS, which considers not only the relationships between features and labels, but also exploits the relationships between instances to select the most informative and important features to enhance the performance of partial label learning. PLFS constructs an adaptive weighted graph to exploit the similarity information among instances, differentiate the label space and weight the feature space, which leads to the selection of a proper feature subset. Extensive experiments over a broad range of benchmark data sets clearly validate the effectiveness of our proposed feature selection approach.