Yifei Wang

Ms. Yifei Wang

orcid

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
11 January 2023 in Informatics
Verified
Journal Article
Open access
PDF file
YWYifei Wang
Yifei Wang
SCShiyang Chen
Shiyang Chen
GCGuobin Chen
Guobin Chen
ESEthan Shurberg
Ethan Shurberg
HLHang Liu
Hang Liu
Pengyu HongPengyu Hong
Pengyu Hong
This work considers the task of representation learning on the attributed relational graph (ARG). Both the nodes and edges in an ARG are associated with attributes/features allowing ARGs to encode rich structural information widely observed in real applications. Existing graph neural networks offer limited ability to capture complex interactions within local structural contexts, which hinders them from taking advantage of the expression power of ARGs. We propose motif convolution module (MCM), a new motif-based graph representation learning technique to better utilize local structural information. The ability to handle continuous edge and node features is one of MCM’s advantages over existing motif-based models. MCM builds a motif vocabulary in an unsupervised way and deploys a novel motif convolution operation to extract the local structural context of individual nodes, which is then used to learn higher level node representations via multilayer perceptron and/or message passing in graph neural networks. When compared with other graph learning approaches to classifying synthetic graphs, our approach is substantially better at capturing structural context. We also demonstrate the performance and explainability advantages of our approach by applying it to several molecular benchmarks.

13 June 2024 in Journal of Biomedical Informatics
Verified
Journal Article
Closed access
YWYifei Wang
Yifei Wang
LWLiqin Wang
Liqin Wang
ZZZhengyang Zhou
Zhengyang Zhou
JLJohn Laurentiev
John Laurentiev
JLJoshua R. Lakin
Joshua R. Lakin
Pengyu HongPengyu Hong
Pengyu Hong

23 June 2025 in Journal of Chemical Information and Modeling
Verified
Journal Article
Open access
YWYifei Wang
Yifei Wang
YLYunrui Li
Yunrui Li
LLLin Liu
Lin Liu
Pengyu HongPengyu Hong
Pengyu Hong
HXHao Xu
Hao Xu
The versatility of multimodal deep learning holds tremendous promise for advancing scientific research and practical applications. As this field continues to evolve, the collective power of cross-modal analysis promises to drive transformative innovations, opening new frontiers in chemical understanding and drug discovery. Hence, we introduce asymmetric contrastive multimodal learning (ACML), a specifically designed approach to enhance molecular understanding and accelerate advancements in drug discovery. ACML harnesses the power of effective asymmetric contrastive learning to seamlessly transfer information from various chemical modalities to molecular graph representations. By combining pretrained chemical unimodal encoders and a shallow-designed graph encoder with 5 layers, ACML facilitates the assimilation of coordinated chemical semantics from different modalities, leading to comprehensive representation learning with efficient training. We demonstrate the effectiveness of this framework through large-scale cross-modality retrieval and isomer discrimination tasks. Additionally, ACML enhances interpretability by revealing chemical semantics in graph presentations and bolsters the expressive power of graph neural networks, as evidenced by improved performance in molecular property prediction tasks from MoleculeNet and Therapeutics Data Commons (TDC). Ultimately, ACML exemplifies its potential to revolutionize molecular representational learning, offering deeper insights into the chemical semantics of diverse modalities and paving the way for groundbreaking advancements in chemical research and drug discovery.

Verified
Journal Article
Open access
PDF file
TYTong Yang
Tong Yang
YWYifei Wang
Yifei Wang
LSLong Sha
Long Sha
JEJan Engelbrecht
Jan Engelbrecht
Pengyu HongPengyu Hong
Pengyu Hong
Knowledge graph (KG) representation learning aims to encode entities and relations into dense continuous vector spaces such that knowledge contained in a dataset could be consistently represented. Dense embeddings trained from KG datasets benefit a variety of downstream tasks such as KG completion and link prediction. However, existing KG embedding methods fell short to provide a systematic solution for the global consistency of knowledge representation. We developed a mathematical language for KG based on an observation of their inherent algebraic structure, which we termed as Knowledgebra. By analyzing five distinct algebraic properties, we proved that the semigroup is the most reasonable algebraic structure for the relation embedding of a general knowledge graph. We implemented an instantiation model, SemE, using simple matrix semigroups, which exhibits state-of-the-art performance on standard datasets. Moreover, we proposed a regularization-based method to integrate chain-like logic rules derived from human knowledge into embedding training, which further demonstrates the power of the developed language. As far as we know, by applying abstract algebra in statistical learning, this work develops the first formal language for general knowledge graphs, and also sheds light on the problem of neural-symbolic integration from an algebraic perspective.

3 April 2026 in International Journal of Medical Informatics
Verified
Journal Article
Closed access
Xinsong DuXinsong Du
Xinsong Du
ANAnna Nagy
Anna Nagy
MOMichael F. Oates
Michael F. Oates
YWYifei Wang
Yifei Wang
XWXinyi Wang
Xinyi Wang
LZLi Zhou
Li Zhou

1 September 2026 in WIREs Computational Molecular Science
Verified
Journal Article
Closed access
YWYifei Wang
Yifei Wang
NBNupur Bansal
Nupur Bansal
Shiyun WaShiyun Wa
Shiyun Wa
SSSimone Sciabola
Simone Sciabola
YWYe Wang
Ye Wang