Xingquan Zuo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xingquan Zuo has a total of 107 co-authors. Here are the top co-authors by number of shared publications:
- Xinchao Zhao
School of Science, Beijing University of Posts and Telecommunications, Beijing, China
14 shared publications Chunlu Wang
8 shared publicationsXing Wan
Zhengzhou Police University
8 shared publications- Gang Chen
School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand
7 shared publications - Hai Huang
Beijing University of Posts and Telecommunications
6 shared publications Jianping Wu
Beijing University of Posts and Telecommunications
5 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 6116-6127
BRP: Query-Efficient Block Revert Patch for Decision-Based Black-Box Adversarial Attack
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 6116-6127
Open AccessBRP: Query-Efficient Block Revert Patch for Decision-Based Black-Box Adversarial Attack
- 30 June 2026
- Published by Springer Nature
- p. 52-64
Compositional Concept-Based Neuron-Level Explanations for Deep Reinforcement Learning
- 30 June 2026
- Published by Springer Nature
- p. 52-64
Compositional Concept-Based Neuron-Level Explanations for Deep Reinforcement Learning
- 23 February 2026
- Published by Springer Nature
- p. 593-609
ERL-BSA: Evolution Strategies-Enhanced Reinforcement Learning for Context-Aware and Workload Balanced Dynamic Bus Scheduling
- 23 February 2026
- Published by Springer Nature
- p. 593-609
ERL-BSA: Evolution Strategies-Enhanced Reinforcement Learning for Context-Aware and Workload Balanced Dynamic Bus Scheduling
- 10 December 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 188
A memetic-branch-and-price algorithm with conflict-minimizing selection strategy for bus scheduling problem
- 10 December 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 188
A memetic-branch-and-price algorithm with conflict-minimizing selection strategy for bus scheduling problem
- 23 October 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 186
Multi-tasking evolutionary learning for constrained multi-modal multi-objective optimization
- 23 October 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 186
Multi-tasking evolutionary learning for constrained multi-modal multi-objective optimization
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 9, 7383-7391
Advancing Community Detection with Graph Convolutional Neural Networks: Bridging Topological and Attributive Cohesion
Community detection, a vital technology for real-world applications, uncovers cohesive node groups (communities) by leveraging both topological and attribute similarities in social networks. However, existing Graph Convolutional Networks (GCNs) trained to maximize modularity often converge to suboptimal solutions. Additionally, directly using human-labeled communities for training can undermine topological cohesiveness by grouping disconnected nodes based solely on node attributes. We address these issues by proposing a novel Topological and Attributive Similarity-based Community detection (TAS-Com) method. TAS-Com introduces a novel loss function that exploits the highly effective and scalable Leiden algorithm to detect community structures with global optimal modularity. Leiden is further utilized to refine human-labeled communities to ensure connectivity within each community, enabling TAS-Com to detect community structures with desirable trade-offs between modularity and compliance with human labels. Experimental results on multiple benchmark networks confirm that TAS-Com can significantly outperform several state-of-the-art algorithms.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 9, 7383-7391
Open AccessAdvancing Community Detection with Graph Convolutional Neural Networks: Bridging Topological and Attributive Cohesion
Community detection, a vital technology for real-world applications, uncovers cohesive node groups (communities) by leveraging both topological and attribute similarities in social networks. However, existing Graph Convolutional Networks (GCNs) trained to maximize modularity often converge to suboptimal solutions. Additionally, directly using human-labeled communities for training can undermine topological cohesiveness by grouping disconnected nodes based solely on node attributes. We address these issues by proposing a novel Topological and Attributive Similarity-based Community detection (TAS-Com) method. TAS-Com introduces a novel loss function that exploits the highly effective and scalable Leiden algorithm to detect community structures with global optimal modularity. Leiden is further utilized to refine human-labeled communities to ensure connectivity within each community, enabling TAS-Com to detect community structures with desirable trade-offs between modularity and compliance with human labels. Experimental results on multiple benchmark networks confirm that TAS-Com can significantly outperform several state-of-the-art algorithms.
- 21 August 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 297
MBCMEA: multi-armed bandit model-based constraint multimodal multi-objective optimization algorithm
- 21 August 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 297
MBCMEA: multi-armed bandit model-based constraint multimodal multi-objective optimization algorithm
- 6 August 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 297
XRL-TO: An explainable reinforcement learning-based approach for bus timetable dynamic optimization
- 6 August 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 297
XRL-TO: An explainable reinforcement learning-based approach for bus timetable dynamic optimization