Zhifei Li

Zhifei Li

Auto-generated profile, based on publicly available information

Zhifei Li

School of computer Science, Hubei university, Wuhan, China

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
19 February 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
ZLZhifei Li
Zhifei Li
HLHai Liu
Hai Liu
Zhaoli ZhangZhaoli Zhang
Zhaoli Zhang
Tingting LiuTingting Liu
Tingting Liu
NXNeal N. Xiong
Neal N. Xiong
Knowledge graph (KG) embedding aims to study the embedding representation to retain the inherent structure of KGs. Graph neural networks (GNNs), as an effective graph representation technique, have shown impressive performance in learning graph embedding. However, KGs have an intrinsic property of heterogeneity, which contains various types of entities and relations. How to address complex graph data and aggregate multiple types of semantic information simultaneously is a critical issue. In this article, a novel heterogeneous GNNs framework based on attention mechanism is proposed. Specifically, the neighbor features of an entity are first aggregated under each relation-path. Then the importance of different relation-paths is learned through the relation features. Finally, each relation-path-based features with the learned weight values are aggregated to generate the embedding representation. Thus, the proposed method not only aggregates entity features from different semantic aspects but also allocates appropriate weights to them. This method can capture various types of semantic information and selectively aggregate informative features. The experiment results on three real-world KGs demonstrate superior performance when compared with several state-of-the-art methods.

30 June 2020 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
ZZZhaoli Zhang
Zhaoli Zhang
ZLZhifei Li
Zhifei Li
HLHai Liu
Hai Liu
NXNeal N. Xiong
Neal N. Xiong
Knowledge graphs are large graph-structured knowledge bases with incomplete or partial information. Numerous studies have focused on knowledge graph embedding to identify the embedded representation of entities and relations, thereby predicting missing relations between entities. Previous embedding models primarily regard (subject entity, relation, and object entity) triplet as translational distance or semantic matching in vector space. However, these models only learn a few expressive features and hard to handle complex relations, i.e., 1-to-N, N-to-1, and N-to-N, in knowledge graphs. To overcome these issues, we introduce a multi-scale dynamic convolutional network (M-DCN) model for knowledge graph embedding. This model features topnotch performance and an ability to generate richer and more expressive feature embeddings than its counterparts. The subject entity and relation embeddings in M-DCN are composed in an alternating pattern in the input layer, which helps extract additional feature interactions and increase the expressiveness. Multi-scale filters are generated in the convolution layer to learn different characteristics among input embeddings. Specifically, the weights of these filters are dynamically related to each relation to model complex relations. The performance of M-DCN on the five benchmark datasets is tested via experiments. Results show that the model can effectively handle complex relations and achieve state-of-the-art link prediction results on most evaluation metrics.

28 May 2025 in Knowledge-Based Systems
Verified
Journal Article
Closed access
KSKe Shi
Ke Shi
YZYan Zhang
Yan Zhang
MZMiao Zhang
Miao Zhang
KXKui Xiao
Kui Xiao
XHXiaoju Hou
Xiaoju Hou
ZLZhifei Li
Zhifei Li

11 April 2013 in Nanotechnology
Verified
Journal Article
Closed access
ZZZhenhang Zhang
Zhenhang Zhang
ZLZhifei Li
Zhifei Li
WYWei Yu
Wei Yu
LKLi Kejie
Li Kejie
ZXZhihong Xie
Zhihong Xie
ZSZhiguo Shi
Zhiguo Shi
Here we describe the utilization of flagellated bacteria as actuators to propel spherical liposomes by attaching bacteria to the liposome surface. Bacteria were stably attached to liposomes using a cross-linking antibody. The effect of the number of attached bacteria on propulsion speed was experimentally determined. The effects of bacterial propulsion on the bacteria-antibody-liposome complex were stochastic. We demonstrated that liposomal mobility increased when bacteria were attached, and the propulsion speed correlated with the number of bacteria.

28 December 2024 in Information Processing & Management
Verified
Journal Article
Closed access
YZYan Zhang
Yan Zhang
XLXiangyu Luo
Xiangyu Luo
JHJing Hu
Jing Hu
MZMiao Zhang
Miao Zhang
KXKui Xiao
Kui Xiao
ZLZhifei Li
Zhifei Li

13 November 2024 in Information Sciences
Verified
Journal Article
Closed access
ZLZhifei Li
Zhifei Li
LCLifan Chen
Lifan Chen
YJYue Jian
Yue Jian
HWHan Wang
Han Wang
YZYue Zhao
Yue Zhao
XHXiaoju Hou
Xiaoju Hou