Junyang Chen | Recommendation System | Young Scientist Award

Published on by Network Science

Assoc. Prof. Dr. Junyang Chen | Recommendation System | Young Scientist Award

Associate Professor at Shenzhen University, China

Dr. Junyang Chen is a tenured Associate Professor at the College of Computer Science and Software Engineering, Shenzhen University, China. His research bridges multimodal data mining, spatiotemporal modeling, and robust recommendation systems. Dr. Chen has developed influential frameworks for multimedia recommendation and user intent modeling, with notable deployments in industry such as Tencent QQ Browser. He is a Senior Member of IEEE/CCF and actively contributes to top-tier conferences and journals in artificial intelligence and multimedia systems.

🔹Professional Profile:

Scopus Profile

Google Scholar Profile

🎓Education Background

  • Ph.D. in Computer Science, University of Macau, Sep 2017 – Dec 2020

💼 Professional Development

  • Associate Professor (Tenured), Shenzhen University, Jan 2025 – Present

  • Assistant Professor, Shenzhen University, Mar 2021 – Dec 2024
    At Shenzhen University, Dr. Chen leads research in multimodal data mining, user behavior analysis, and spatiotemporal modeling. He has collaborated with leading industry players, including Tencent, where his algorithms significantly improved engagement metrics such as CTR and recommendation accuracy.

🔬Research Focus

  • Multimodal Data Mining

  • Robust Recommendation Systems in Open Environments

  • Spatiotemporal User Modeling

  • Few-shot and Zero-shot Learning

  • Graph Representation Learning

  • Social Media Behavior Analysis

📈Author Metrics:

  • Publications: 80+ peer-reviewed papers

    • 22 CCF-A / SCI Q1 as first/corresponding author

    • 21 CCF-B / SCI Q2 papers

  • Citations: 1,400+ (Google Scholar)

  • Google Scholar: Link

🏆Awards and Honors:

  • 2024 Shenzhen AI Natural Science Award (First Recipient)

  • 2024 Tencent “Rhinoceros Bird” Young Faculty Research Fund

  • 2020 National Postdoctoral Forum Best Paper Award (1st Class)

  • Principal Investigator of 1 NSFC project and 3 provincial/municipal projects

  • Editorial and Leadership Roles:

    • Guest Editor, IEEE Transactions on Computational Social Systems

    • Executive Committee Member, CCF Multimedia & Collaborative Computing

    • PC Member: AAAI, ACL, ACM MM, NeurIPS, and more

📝Publication Top Notes

1. LUSTER: Link Prediction Utilizing Shared-Latent Space Representation in Multi-Layer Networks

  • Authors: Ruohan Yang, Muhammad Asif Ali, Huan Wang, Junyang Chen, Di Wang

  • Conference: The Web Conference (WWW), 2025

  • Summary: This paper introduces LUSTER, an end-to-end framework designed for link prediction in multi-layer networks. It addresses the limitations of existing methods by leveraging a shared-latent space representation to capture inter-layer dependencies. The framework comprises four modules: representation extractor, latent space learner, complementary enhancer, and link predictor. Experimental results demonstrate that LUSTER outperforms state-of-the-art methods, achieving up to a 15.87% improvement in AUC metrics. ​OpenReview

2. Deconfound Semantic Shift and Incompleteness in Incremental Few-shot Semantic Segmentation

  • Authors: Yirui Wu, Yuhang Xia, Hao Li, Lixin Yuan, Junyang Chen, Jun Liu, Tong Lu, Shaohua Wan

  • Conference: Proceedings of the AAAI Conference on Artificial Intelligence, 2025

  • Summary: This study tackles the challenges of semantic shift and data incompleteness in incremental few-shot semantic segmentation. The authors propose a dual-stream incremental learning framework that disentangles semantic shifts and addresses data incompleteness, enhancing the model’s adaptability to new classes with limited data.​

3. Reliable Service Recommendation: A Multi-modal Adversarial Method for Personalized Recommendation under Uncertain Missing Modalities

  • Authors: Junyang Chen, Ruohan Yang, Jingcai Guo, Huan Wang, Kaishun Wu, Liangjie Zhang

  • Journal: IEEE Transactions on Services Computing, 2025

  • Summary: The paper presents a robust adversarial learning framework for personalized service recommendation, particularly effective when dealing with uncertain or missing data modalities. The proposed method enhances recommendation reliability by adapting to incomplete multi-modal data scenarios.​

4. Adaptive Density Estimation for Personalized Recommendations Across Varied User Activity Levels

  • Authors: Weiwen Liu, Hao Zhu, Jun Yu, Liang Zheng, Jun Yin, Ruijia Liang, Xiaoyu Liu, Junyang Chen, Victor C.M. Leung

  • Journal: IEEE Transactions on Computational Social Systems, 2025

  • Summary: This research introduces a user-activity-aware density estimation technique aimed at improving personalized recommendation systems. By accounting for varying levels of user activity, the proposed method enhances recommendation performance for both highly active and less active users. ​

5. Unveiling User Interests: A Deep User Interest Exploration Network for Sequential Location Recommendation

  • Authors: Junyang Chen, Jingcai Guo, Qin Zhang, Kaishun Wu, Liangjie Zhang, Victor C.M. Recommendation systemLeung, Huan Wang, Zhiguo Gong

  • Journal: Information Sciences, Volume 689, Article 121416, 2025

  • Summary: The authors propose the Deep User Interest Exploration Network (DUIEN) to enhance sequential location recommendation systems. DUIEN employs a bidirectional neural network with a Cloze objective to predict masked points of interest (POIs) within user trajectories and integrates a user interest exploration layer that utilizes POI tag information. This approach effectively captures the evolving interests of users, leading to improved recommendation accuracy

Conclusion:

Assoc. Prof. Dr. Junyang Chen exemplifies the ideal candidate for the Research for Young Scientist Award through a combination of:

  • Cutting-edge and practical research in Recommendation Systems

  • Demonstrated real-world impact via industry deployments

  • Recognized leadership in high-impact publishing and community service

  • Strategic research directions that align with future challenges in AI personalization, multimodal learning, and robust modeling

Given his academic maturity, research depth, early-career accomplishments, and societal relevance of his work, Dr. Chen is a highly deserving nominee for this award. His work is not only forward-looking but also sets foundational pillars for next-generation intelligent systems.

Lin Yu Rou |  Machine Learning | Best Researcher Award

Published on by Network Science

Ms. Lin Yu Rou |  Machine Learning | Best Researcher Award

Software Development Engineer, China Trust Commercial Bank, Taiwan

Yuruo Lin is a passionate researcher and aspiring data scientist with a strong foundation in information and finance management. With hands-on experience in data analytics, machine learning, and healthcare informatics, she actively engages in interdisciplinary research projects, focusing on practical applications that merge technology and social impact. Her academic journey is marked by leadership, innovation, and a commitment to empowering communities through data-driven solutions.

🔹Professional Profile:

Orcid Profile

🎓Education Background

  1. Master’s in Information and Finance Management
    National Taipei University of Technology, Taiwan
    Sep 2022 – Jun 2024

    • Honorable Mention in 2023 Capstone Project Competition

    • Participant in “STEM & Female Research Talent Cultivation Program (2022)”

  2. Bachelor’s in Information Management
    National Taipei University of Nursing and Health Sciences, Taiwan
    Sep 2018 – Jun 2022

    • 2nd Place, 2021 National Collegiate Information Application Innovation Competition

    • Published research on the impact of COVID-19 on hospital quality

    • President, IT Volunteer Club; led USR project and received Outstanding Club and Officer Scholarship

💼 Professional Development

Yuruo has collaborated on diverse academic and practical research projects, combining statistical methods with machine learning and data visualization to address real-world problems. She developed predictive models for ESG performance using ensemble learning, analyzed hospital service quality amid the COVID-19 pandemic, and experimented with algorithmic trading strategies. Her work spans financial analytics, public health equity, and VR-based elderly care solutions.

🔬Research Focus

  • Data Science and Machine Learning

  • Financial and Investment Analytics

  • Healthcare Informatics and Public Health Data

  • Human-Computer Interaction (HCI)

  • Media Analytics for ESG Performance

  • Social Impact Technology (VR, USR Projects)

📈Author Metrics:

Yuruo Lin is the first author of a peer-reviewed research article titled “How can media attention reveal ESG improvement opportunities? A multi-algorithm ML-based approach for Taiwan’s electronics industry,” published in the Elsevier journal Expert Systems with Applications in 2025. This journal is indexed in SCI and Scopus, with a strong impact factor in the fields of artificial intelligence and applied computing. Her publication explores media-driven ESG analytics using ensemble machine learning and clustering techniques, demonstrating both technical depth and relevance to sustainability research. The work has garnered academic attention and serves as a foundation for her growing research profile in data science and ESG modeling.

🏆Awards and Honors:

  • Honorable Mention – 2023 Capstone Project Competition, NTUT

  • 2nd Place – 2021 National Collegiate Information Application Innovation Competition (VR Therapy)

  • Outstanding Club Leadership – IT Volunteer Club, USR Project, Ministry of Education

  • Multiple Awards – National Innovation Proposal Competitions (2020–2021)

  • Scholarship – Officer Scholarship for Club Leadership

📝Publication Top Notes

1. How can media attention reveal ESG improvement opportunities? A multi-algorithm machine learning-based approach for Taiwan’s electronics industry

Journal: The North American Journal of Economics and Finance
Publisher: Elsevier
Publication Date: May 2025
DOI: 10.1016/j.najef.2025.102431
ISSN: 1062-9408
Contributors: Shu Ling Lin, Yu Rou Lin, Xiao Jin
Indexing: Scopus, SSCI
Abstract Summary:
This study applies ensemble machine learning algorithms—including Naive Bayes, Support Vector Machines, Random Forest, and Neural Networks—combined with clustering and semi-supervised learning to investigate how media attention can serve as a predictive signal for ESG performance changes in Taiwan’s electronics industry. The findings highlight the potential of media-driven analytics in enhancing ESG investment strategies and corporate monitoring.

2. Exploring the Relationship between Corporate ESG Ratings and Media Attention through Machine Learning: Predictive Model for the Taiwanese Electronics Industry

Author: Yu Rou Lin
Institution: National Taipei University of Technology
Degree: Master’s in Information and Finance Management
Status: Completed (June 2024)
Contribution: Original draft, research design, and full implementation of machine learning pipeline
Focus: The thesis investigates the correlation between ESG ratings and media sentiment, using real market data and various machine learning models, and serves as the foundational research for the later published journal article.

Conclusion:

In summary, Ms. Yu Rou Lin is an outstanding candidate for the Best Researcher Award in Machine Learning. Her work exemplifies the fusion of technical rigor and societal relevance, with achievements that reflect intellectual curiosity, practical application, and academic leadership.

Her potential for future growth is immense, especially as she continues to refine her research contributions and engage with global scientific communities.

Zhi Gao | Vision-Language Models | Best Researcher Award

Published on by Network Science

Dr. Zhi Gao | Vision-Language Models | Best Researcher Award

Postdoctoral Research Fellow at Peking University, China.

Dr. Zhi Gao is a Postdoctoral Research Fellow at the School of Intelligence Science and Technology, Peking University. His research focuses on multimodal learning, vision-language models, and human-robot interaction. With expertise in computer vision and machine learning, he explores the development of intelligent agents capable of understanding and interacting with complex environments.

Professional Profile:

Google Scholar Profile

Education Background 🎓📖

  • Ph.D. in Computer Science and Technology, Beijing Institute of Technology (2018–2023)
  • Master in Computer Science and Technology, Beijing Institute of Technology (2017–2018)
  • B.S. in Computer Science and Technology, Beijing Institute of Technology (2013–2017)

Professional Development 📈💡

Dr. Gao is currently a Postdoctoral Research Fellow at Peking University under the supervision of Prof. Song-Chun Zhu, focusing on multimodal learning and agent development. Concurrently, he serves as a Research Scientist at the Beijing Institute for General Artificial Intelligence, working on vision-language models in the Machine Learning Lab. His research integrates deep learning, data representation, and human-centered AI to enhance machine perception and reasoning.

Research Focus 🔬📖

His work spans computer vision and machine learning, particularly in developing multimodal agents capable of learning from human-robot interactions and adapting to dynamic environments. He is also interested in leveraging the geometry of data space to address challenges such as insufficient annotations and distribution shifts.

Author Metrics

  • Publications in top-tier AI and computer vision conferences and journals
  • Research contributions in multimodal intelligence, vision-language understanding, and AI-driven reasoning

Awards & Honors 🏆🎖️

  • National Science Foundation for Young Scientists of China (2025–2027) for research on Riemannian multimodal large language models for video understanding
  • Distinguished Dissertation Award from SIGAI CHINA (October 202X)

Publication Top Notes

1. A Hyperbolic-to-Hyperbolic Graph Convolutional Network

Authors: Jindou Dai, Yuwei Wu, Zhi Gao, Yunde Jia
Published in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 154-163
Abstract: This paper introduces a hyperbolic-to-hyperbolic graph convolutional network (H2H-GCN) that operates directly on hyperbolic manifolds. The proposed method includes a manifold-preserving graph convolution with hyperbolic feature transformation and neighborhood aggregation, avoiding distortions from tangent space approximations. Extensive experiments demonstrate substantial improvements in tasks such as link prediction, node classification, and graph classification.

openaccess.thecvf.com

2. Curvature Generation in Curved Spaces for Few-Shot Learning

Authors: Zhi Gao, Yuwei Wu, Yunde Jia, Mehrtash Harandi
Published in: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 8671-8680
Abstract: This research addresses few-shot learning by proposing task-aware curved embedding spaces using hyperbolic geometry. By generating task-specific embedding spaces with appropriate curvatures, the method enhances the generality of embeddings. The study leverages intra-class and inter-class context information to create discriminative class prototypes, showing benefits over existing embedding methods in both inductive and transductive few-shot learning scenarios.

3. Deep Convolutional Network with Locality and Sparsity Constraints for Texture Classification

Authors: Xiaoyu Bu, Yuwei Wu, Zhi Gao, Yunde Jia
Published in: Pattern Recognition, Volume 91, 2019, Pages 34-46
Abstract: This paper presents a deep convolutional network incorporating locality and sparsity constraints to improve texture classification. The proposed model enhances feature representation by enforcing local connectivity and sparse activation, leading to improved classification performance on texture datasets.

4. Meta-Causal Learning for Single Domain Generalization

Authors: Jianlong Chen, Zhi Gao, Xiaodan Wu, Jiebo Luo
Published in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Abstract: The study introduces a meta-causal learning framework aimed at enhancing generalization in single-domain settings. By leveraging causal relationships within the data, the approach seeks to improve model robustness when applied to unseen domains, addressing challenges in domain generalization.

5. A Robust Distance Measure for Similarity-Based Classification on the SPD Manifold

Authors: Zhi Gao, Yuwei Wu, Mehrtash Harandi, Yunde Jia
Published in: IEEE Transactions on Neural Networks and Learning Systems, Volume 31, Issue 9, 2019, Pages 3230-3244
Abstract: This research proposes a robust distance measure tailored for similarity-based classification tasks on the Symmetric Positive Definite (SPD) manifold. The developed measure enhances classification accuracy by effectively capturing the intrinsic geometry of the SPD manifold, demonstrating robustness in various similarity-based classification scenarios.

Conclusion:

Dr. Zhi Gao is a strong candidate for the Best Researcher Award, given his groundbreaking contributions in vision-language models, hyperbolic learning, and multimodal AI. His strong academic background, top-tier publications, and national recognition make him a well-qualified nominee. However, to further strengthen his impact, he could focus on industry collaborations, real-world AI applications, and global AI leadership.

Verdict: ✅ Highly suitable for the Best Researcher Award with minor areas of improvement for long-term impact.