Shanqi Liu

Shanqi Liu

Auto-generated profile, based on publicly available information

Shanqi Liu

College of Computer Science and Technology, Zhejiang University, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 January 2024 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
SLSiqi Li
Siqi Li
JCJun Chen
Jun Chen
SLShanqi Liu
Shanqi Liu
CZChengrui Zhu
Chengrui Zhu
GTGuanzhong Tian
Guanzhong Tian
YLYong Liu
Yong Liu
Model compression methods are being developed to bridge the gap between the massive scale of neural networks and the limited hardware resources on edge devices. Since most real-world applications deployed on resource-limited hardware platforms typically have multiple hardware constraints simultaneously, most existing model compression approaches that only consider optimizing one single hardware objective are ineffective. In this article, we propose an automated pruning method called multi-constrained model compression (MCMC) that allows for the optimization of multiple hardware targets, such as latency, floating point operations (FLOPs), and memory usage, while minimizing the impact on accuracy. Specifically, we propose an improved multi-objective reinforcement learning (MORL) algorithm, the one-stage envelope deep deterministic policy gradient (DDPG) algorithm, to determine the pruning strategy for neural networks. Our improved one-stage envelope DDPG algorithm reduces exploration time and offers greater flexibility in adjusting target priorities, enhancing its suitability for pruning tasks. For instance, on the visual geometry group (VGG)-16 network, our method achieved an 80% reduction in FLOPs, a $2.31\times$ reduction in memory usage, and a $1.92\times$ acceleration, with an accuracy improvement of 0.09% compared with the baseline. For larger datasets, such as ImageNet, we reduced FLOPs by 50% for MobileNet-V1, resulting in a $4.7\times$ faster speed and $1.48\times$ memory compression, while maintaining the same accuracy. When applied to edge devices, such as JETSON XAVIER NX, our method resulted in a 71% reduction in FLOPs for MobileNet-V1, leading to a $1.63\times$ faster speed, $1.64\times$ memory compression, and an accuracy improvement.

18 April 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
SLShanqi Liu
Shanqi Liu
WLWeiwei Liu
Weiwei Liu
WCWenzhou Chen
Wenzhou Chen
GTGuanzhong Tian
Guanzhong Tian
JCJun Chen
Jun Chen
YLYong Liu
Yong Liu
Recently value-based centralized training with decentralized execution (CTDE) multi-agent reinforcement learning (MARL) methods have achieved excellent performance in cooperative tasks. However, the most representative method among these methods, Q-network MIXing (QMIX), restricts the joint action $Q$ values to be a monotonic mixing of each agent’s utilities. Furthermore, current methods cannot generalize to unseen environments or different agent configurations, which is known as ad hoc team play situation. In this work, we propose a novel $Q$ values decomposition that considers both the return of an agent acting on its own and cooperating with other observable agents to address the nonmonotonic problem. Based on the decomposition, we propose a greedy action searching method that can improve exploration and is not affected by changes in observable agents or changes in the order of agents’ actions. In this way, our method can adapt to ad hoc team play situation. Furthermore, we utilize an auxiliary loss related to environmental cognition consistency and a modified prioritized experience replay (PER) buffer to assist training. Our extensive experimental results show that our method achieves significant performance improvements in both challenging monotonic and nonmonotonic domains, and can handle the ad hoc team play situation perfectly.

1 June 2024 in International Journal of Artificial Intelligence and Robotics Research
Verified
Journal Article
Closed access
WTWeihao Tan
Weihao Tan
WZWentao Zhang
Wentao Zhang
SLShanqi Liu
Shanqi Liu
LZLongtao Zheng
Longtao Zheng
XWXinrun Wang
Xinrun Wang
BABo An
Bo An

26 November 2021
Verified
Conference Paper
Closed access
WLWeiwei Liu
Weiwei Liu
SLShanqi Liu
Shanqi Liu
JYJian Yang
Jian Yang
YLYong Liu
Yong Liu
Reinforcement learning is one of the algorithms used in multi-agent systems to promote agent cooperation. However, most current multi-agent reinforcement learning algorithms improve the communication capabilities of agents for cooperation, but the overall communication is costly and even harmful due to bandwidth limitations. In addition, de-centralized execution cannot generate joint actions, which is not conducive to cooperation. Therefore, we proposed the Hierarchical Group Cooperation Network (HGCN). Advanced strategy, Group Network (GroNet), learns to group all agents based on their state rather than their location. The Low-level strategy, Group Cooperation Network (GCoNet), is a method of centralized training and centralized execution within a group, which effectively promotes agent collaboration. Finally, we validated our method in various experiments.