Jie Liu

Dr. Jie Liu


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
26 February 2025 in Journal of Artificial Intelligence Research
Verified
Journal Article
Closed access
PDF file
CWChuyuan Wei
Chuyuan Wei
KDKe Duan
Ke Duan
Shengda ZhuoShengda Zhuo
Shengda Zhuo
HWHongchun Wang
Hongchun Wang
SHShuqiang Huang
Shuqiang Huang
JLJie Liu
Jie Liu
Recommender systems have long struggled with challenges such as cold start and data sparsity, which can lead to poor recommendation performance. While previous approaches have attempted to address these issues by incorporating side information, they often introduce noise, lack flexibility for data expansion, and suffer from inconsistent data quality—factors that hinder accurate user preference inference and reduce recommendation performance. With the vast knowledge bases and advanced reasoning capabilities of large language models (LLMs), these models are particularly well-suited to supplement auxiliary information and capture implicit user intent. To address these challenges, we propose a novel framework, ER2ALM, which leverages the capabilities of LLMs enhanced by Retrieval-Augmented Generation (RAG) to improve recommendation outcomes. Our framework specifically addresses the challenges by flexibly and accurately augmenting auxiliary information and capturing users’ implicit preferences and interests. Additionally, to mitigate the risk of introducing noise, we incorporate a noise reduction strategy to ensure the reliability of the augmented information. Experimental validation on two real-world datasets demonstrates the efficacy of our approach, significantly enhancing both the accuracy and robustness of recommendations compared to state-of-the-art methods. This demonstrates the potential of our framework as a new paradigm for preference mining in recommendation systems.

23 October 2019 in IEEE Access
Verified
Journal Article
Open access
YPYihe Pang
Yihe Pang
JLJie Liu
Jie Liu
LLLizhen Liu
Lizhen Liu
ZYZhengtao Yu
Zhengtao Yu
KZKai Zhang
Kai Zhang

1 August 2017
Verified
Conference Paper
Closed access
YZYongchang Zhang
Yongchang Zhang
JLJie Liu
Jie Liu
Model predictive current control (MPCC) is a powerful control strategy for the control of three-phase power converters. Conventional MPCC achieves good steady state performance and quick dynamic response by selecting the optimal voltage vector. However, this method is highly dependent on the accuracy of the model and parameters, which means that the steady state performance will deteriorate when the parameters become inaccurate. To solve this problem, model-free predictive current control (MFPCC) has been proposed in the literature, which only needs the information of sensed current and eliminates the use of system model. However, when applying MFPCC to PWM rectifiers, it presents high power spikes at steady state. This paper proposes an improved MFPCC to eliminate the high power spikes. Both Simulation and experimental results are presented to validate the effectiveness of the proposed method.

4 February 2025 in Expert Systems with Applications
Verified
Journal Article
Closed access
JWJiong Wang
Jiong Wang
QZQing Zhang
Qing Zhang
JLJie Liu
Jie Liu
XWXiaoyi Wang
Xiaoyi Wang
MXMingying Xu
Mingying Xu
JZJianshe Zhou
Jianshe Zhou

8 October 2021 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
YMYuhao Ma
Yuhao Ma
JZJian Zhu
Jian Zhu
JLJie Liu
Jie Liu

11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
LXLinhuang Xie
Linhuang Xie
SGShihao Gao
Shihao Gao
JLJie Liu
Jie Liu
MYMing Yin
Ming Yin
TJTaisong Jin
Taisong Jin
The powerful capability of HyperGraph Neural Networks (HGNNs) in modeling intricate, high-order relationships among multiple data samples stems primarily from their ability to aggregate both the direct neighborhood features of individual nodes and those associated with hyperedges. However, the limited scope of feature propagation in existing HGNNs significantly reduces the utilization of hypergraph information, exacerbating over-squashing and over-smoothing issues. To this end, we propose a novel K-hop HyperGraph Neural Network (KHGNN) to facilitate the interactions of distant nodes and hyperedges. Specifically, the bisection nested convolution based on HyperGINE is employed to extract features from nodes, hyperedges, and structures along all shortest paths between nodes or hyperedges, providing representations of long-distance relationships. With these comprehensive path features, nodes and hyperedges are guided to aggregate distant information while learning their complex relationships. The extensive experiments, particularly on long-range graph datasets, demonstrate that the proposed method achieves SOTA performance compared to existing HGNNs and graph neural networks.