Shengze Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shengze Li has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Hao Jiang
Academy of Military Sciences, Beijing, China
3 shared publications - Jieyuan Zhang
Chinese Academy of Military Science, Beijing, China
3 shared publications - Xinhai Xu
Academy of Military Sciences, Beijing, China
3 shared publications - Donghong Liu
Academy of Military Sciences, Beijing, China
2 shared publications - Angsheng Li
Beihang University
1 shared publication - Chunyang Liu
Didi Chuxing, Beijing, China
1 shared publication
Latest Publications
- 24 April 2026
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 17 (6) , 265
Ahafed: accelerated hierarchical aggregation for heterogeneous federated learning in multi-UAV networks
- 24 April 2026
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 17 (6) , 265
Ahafed: accelerated hierarchical aggregation for heterogeneous federated learning in multi-UAV networks
- Open Access
Hyperbolic Continuous Structural Entropy for Hierarchical Clustering
Hierarchical clustering is a fundamental machine-learning technique for grouping data points into dendrograms. However, existing hierarchical clustering methods encounter two primary challenges: 1) Most methods specify dendrograms without a global objective. 2) Graph-based methods often neglect the significance of graph structure, optimizing objectives on complete or static predefined graphs. In this work, we propose Hyperbolic Continuous Structural Entropy neural networks, namely HypCSE, for structure-enhanced continuous hierarchical clustering. Our key idea is to map data points in the hyperbolic space and minimize the relaxed continuous structural entropy (SE) on structure-enhanced graphs. Specifically, we encode graph vertices in hyperbolic space using hyperbolic graph neural networks and minimize approximate SE defined on graph embeddings. To make the SE objective differentiable for optimization, we reformulate it into a function using the lowest common ancestor (LCA) on trees and then relax it into continuous SE (CSE) by the analogy of hyperbolic graph embeddings and partitioning trees. To ensure a graph structure that effectively captures the hierarchy of data points for CSE calculation, we employ a graph structure learning (GSL) strategy that updates the graph structure during training. Extensive experiments on seven datasets demonstrate the superior performance of HypCSE.
Open AccessHyperbolic Continuous Structural Entropy for Hierarchical Clustering
Hierarchical clustering is a fundamental machine-learning technique for grouping data points into dendrograms. However, existing hierarchical clustering methods encounter two primary challenges: 1) Most methods specify dendrograms without a global objective. 2) Graph-based methods often neglect the significance of graph structure, optimizing objectives on complete or static predefined graphs. In this work, we propose Hyperbolic Continuous Structural Entropy neural networks, namely HypCSE, for structure-enhanced continuous hierarchical clustering. Our key idea is to map data points in the hyperbolic space and minimize the relaxed continuous structural entropy (SE) on structure-enhanced graphs. Specifically, we encode graph vertices in hyperbolic space using hyperbolic graph neural networks and minimize approximate SE defined on graph embeddings. To make the SE objective differentiable for optimization, we reformulate it into a function using the lowest common ancestor (LCA) on trees and then relax it into continuous SE (CSE) by the analogy of hyperbolic graph embeddings and partitioning trees. To ensure a graph structure that effectively captures the hierarchy of data points for CSE calculation, we employ a graph structure learning (GSL) strategy that updates the graph structure during training. Extensive experiments on seven datasets demonstrate the superior performance of HypCSE.
- Open Access
- 19 April 2025
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 11 (6) , 1-17
Hierarchical reinforcement learning based on macro actions
- 19 April 2025
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 11 (6) , 1-17
Open AccessHierarchical reinforcement learning based on macro actions
- Open Access
- 17 July 2024
- Published by Elsevier in Neural Networks
- Vol. 179, 106552
Generative subgoal oriented multi-agent reinforcement learning through potential field
- 17 July 2024
- Published by Elsevier in Neural Networks
- Vol. 179, 106552
Open AccessGenerative subgoal oriented multi-agent reinforcement learning through potential field
- Open Access
- 31 December 2023
- Published by MDPI AG in Mathematics
- Vol. 12 (1) , 141
LIDAR Point Cloud Augmentation for Dusty Weather Based on a Physical Simulation
LIDAR is central to the perception systems of autonomous vehicles, but its performance is sensitive to adverse weather. An object detector trained by deep learning with the LIDAR point clouds in clear weather is not able to achieve satisfactory accuracy in adverse weather. Considering the fact that collecting LIDAR data in adverse weather like dusty storms is a formidable task, we propose a novel data augmentation framework based on physical simulation. Our model takes into account finite laser pulse width and beam divergence. The discrete dusty particles are distributed randomly in the surrounding of LIDAR sensors. The attenuation effects of scatters are represented implicitly with extinction coefficients. The coincidentally returned echoes from multiple particles are evaluated by explicitly superimposing their power reflected from each particle. Based on the above model, the position and intensity of real point clouds collected from dusty weather can be modified. Numerical experiments are provided to demonstrate the effectiveness of the method.
- 31 December 2023
- Published by MDPI AG in Mathematics
- Vol. 12 (1) , 141
Open AccessLIDAR Point Cloud Augmentation for Dusty Weather Based on a Physical Simulation
LIDAR is central to the perception systems of autonomous vehicles, but its performance is sensitive to adverse weather. An object detector trained by deep learning with the LIDAR point clouds in clear weather is not able to achieve satisfactory accuracy in adverse weather. Considering the fact that collecting LIDAR data in adverse weather like dusty storms is a formidable task, we propose a novel data augmentation framework based on physical simulation. Our model takes into account finite laser pulse width and beam divergence. The discrete dusty particles are distributed randomly in the surrounding of LIDAR sensors. The attenuation effects of scatters are represented implicitly with extinction coefficients. The coincidentally returned echoes from multiple particles are evaluated by explicitly superimposing their power reflected from each particle. Based on the above model, the position and intensity of real point clouds collected from dusty weather can be modified. Numerical experiments are provided to demonstrate the effectiveness of the method.
- Open Access
- 22 February 2023
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 9 (5) , 4911-4922
Efficient state representation with artificial potential fields for reinforcement learning
In the complex tasks environment, efficient state feature learning is a key factor to improve the performance of the agent’s policy. When encountering a similar new environment, reinforcement learning agents usually need to learn from scratch. However, humans naturally have a common sense of the environment and are able to use prior knowledge to extract environmental state features. Although the prior knowledge may not be fully applicable to the new environment, it is able to speed up the learning process of the state feature. Taking this inspiration, we propose an artificial potential field-based reinforcement learning (APF-RL) method. The method consists of an artificial potential field state feature abstractor (APF-SA) and an artificial potential field intrinsic reward model (APF-IR). The APF-SA can introduce human knowledge to accelerate the learning process of the state feature. The APF-IR can generate an intrinsic reward to reduce the invalid exploration and guide the learning of the agent’s policy. We conduct experiments on PySC2 with different mini-games. The experimental results show that the APF-RL method achieves improvement in the learning efficiency compared to the benchmarks.
- 22 February 2023
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 9 (5) , 4911-4922
Open AccessEfficient state representation with artificial potential fields for reinforcement learning
In the complex tasks environment, efficient state feature learning is a key factor to improve the performance of the agent’s policy. When encountering a similar new environment, reinforcement learning agents usually need to learn from scratch. However, humans naturally have a common sense of the environment and are able to use prior knowledge to extract environmental state features. Although the prior knowledge may not be fully applicable to the new environment, it is able to speed up the learning process of the state feature. Taking this inspiration, we propose an artificial potential field-based reinforcement learning (APF-RL) method. The method consists of an artificial potential field state feature abstractor (APF-SA) and an artificial potential field intrinsic reward model (APF-IR). The APF-SA can introduce human knowledge to accelerate the learning process of the state feature. The APF-IR can generate an intrinsic reward to reduce the invalid exploration and guide the learning of the agent’s policy. We conduct experiments on PySC2 with different mini-games. The experimental results show that the APF-RL method achieves improvement in the learning efficiency compared to the benchmarks.