Ms. Yanyan Liu | Topic model | Best Researcher Award
PHD Candidate at University of Macau, China
Yanyan Liu is a dedicated researcher specializing in Data Mining with expertise in neural topic modeling, natural language processing, and recommendation systems. She is currently pursuing her Ph.D. in Computer Science at the University of Macau, focusing on developing innovative machine-learning frameworks to enhance topic modeling and social influence learning. With a strong academic foundation and a passion for advancing knowledge in her field, she has published in esteemed journals and conferences, including Knowledge-Based Systems and ACM CIKM.
Profile
Education Background
- Doctorate in Computer Science
University of Macau | Aug 2020 – Present
Major Courses: Natural Language Processing, Web Mining, Computer Vision, and Pattern Recognition. - Bachelor of Computer Science and Technology
Hunan University | Sep 2016 – Jun 2020
GPA: 85.21/100
Major Courses: Database (94/100), Computer Network, Advanced Programming, Data Structure, Computer System.
Professional Experience
Yanyan Liu has been involved in cutting-edge research on neural topic modeling, where she proposed:
- An efficient energy-based neural topic model integrating a learnable topic prior constraint.
- A novel topic-guided debiased contrastive learning framework to enhance topic discrimination.
She has also contributed to social influence learning models for recommendation systems, advancing the field of personalized recommendations.
Her research focuses on Data Mining, Natural Language Processing, Web Mining, Computer Vision, and Pattern Recognition, with a particular interest in applying these technologies for real-world challenges.
Author Metrics
Yanyan Liu has established herself as an emerging researcher in the field of data mining and machine learning, with a growing portfolio of impactful publications in reputed venues. Her work has been featured in journals such as Knowledge-Based Systems and conferences like the ACM International Conference on Information and Knowledge Management (CIKM), demonstrating her ability to address complex problems in neural topic modeling and recommendation systems. Through her innovative contributions, she has garnered recognition for proposing efficient frameworks and methodologies that advance understanding in these domains. Her publications reflect her commitment to high-quality research and her potential to make significant strides in the field.
1. Cycling Topic Graph Learning for Neural Topic Modeling
- Authors: Liu, Y., Gong, Z.
- Journal: Knowledge-Based Systems
- Year: 2025
- Volume: 310
- DOI/Article ID: 112905
- Citations: 0 (as of now).
- Summary:
This paper introduces a novel approach to neural topic modeling using cycling topic graph learning. The method enhances the interpretability and efficiency of topic models by incorporating graph-based structures to represent relationships among topics dynamically. This energy-efficient framework leverages embeddings to achieve improved coherence and relevance in extracted topics.
2. Social Influence Learning for Recommendation Systems
- Authors: Chen, X., Lei, P.I., Sheng, Y., Liu, Y., Gong, Z.
- Conference: 33rd ACM International Conference on Information and Knowledge Management (CIKM)
- Year: 2024
- Pages: 312–322
- Citations: 1 (as of now).
- Summary:
This conference paper proposes a social influence learning framework tailored for recommendation systems. It explores the role of social connections in shaping user preferences and integrates social influence modeling with machine learning techniques to enhance recommendation accuracy. The model accounts for dynamic social interactions, improving both predictive power and user satisfaction.
Conclusion
Ms. Yanyan Liu is a highly promising researcher with significant achievements in neural topic modeling and recommendation systems. Her innovative contributions, publications in esteemed venues, and dedication to advancing machine learning and data mining make her a strong candidate for the Best Researcher Award. While her citation metrics and collaborative efforts could benefit from further growth, her potential for impactful research and her current accomplishments position her as an excellent choice for this honor.
Her dedication to tackling complex problems and her innovative approach to addressing them not only align with the criteria for the award but also set a strong foundation for her future contributions to the academic and professional world.