Skip to menu Skip to content Skip to footer
Professor Hongzhi Yin
Professor

Hongzhi Yin

Email: 
Phone: 
+61 7 336 54739

Overview

Background

Prof. Hongzhi Yin works as an ARC Future Fellow and Professor and director of the Responsible Big Data Intelligence Lab (RBDI) at The University of Queensland, Australia. He has made notable contributions to recommendation systems, structured foundation model, spatial-temporal prediction, LLM and ChatBI, and decentralized and edge intelligence. He has received numerous awards and recognition for his research achievements. He has been named to IEEE Computer Society’s AI’s 10 to Watch 2022 and Field Leader of Data Mining & Analysis in The Australian's Research 2020 magazine. In addition, he has received the prestigious 2023 Young Tall Poppy Science Awards, Australian Research Council Future Fellowship 2021, the Discovery Early Career Researcher Award 2016, UQ Foundation Research Excellence Award 2019, 2024 and 2025 Computer Science in Australia Leader Award, AI 2000 Most Influential Scholar Honorable Mention in Data Mining (2022-2025), 2024 and 2025 ScholarGPS Highly Ranked Scholar (top 0.05%). His research has won 8 international and national Best Paper Awards, including Best Student Full Paper Award at CIKM 2024, Best Paper Award - Honorable Mention at WSDM 2023, Best Paper Award at ICDE 2019, Best Student Paper Award at DASFAA 2020, Best Paper Award Nomination at ICDM 2018, ACM Computing Reviews' 21 Annual Best of Computing Notable Books and Articles, Best Paper Award at ADC 2018 and 2016. His Ph.D. thesis won Peking University Outstanding Ph.D. Dissertation Award 2014 and CCF Outstanding Ph.D. Dissertation Award (Nomination) 2014. He has ten conference papers recognized as the Most Influential Papers in Paper Digest, including KDD 2021 and 2013, AAAI 2021, SIGIR 2022, WWW 2023 and 2021, CIKM 2021, 2019, 2016, and 2015. He has published 400 papers with an H-index of 91 (29000+ citations), including 290+ CCF A/CORE A* and 90+ CCF B/CORE A, such as ICML, ICLR, NeurIPS, KDD, SIGIR, WWW, ACL, WSDM, SIGMOD, VLDB, ICDE, AAAI, IJCAI, ACM Multimedia, ECCV, IEEE TKDE, TNNL, VLDB Journal, and ACM TOIS. He has been the leading author (first/co-first author or corresponding author) for 300. He has been an SPC/PC member for many top conferences, such as AAAI, IJCAI, KDD, ICML, ICLR, NeurIPS, SIGIR, WWW, WSDM, VLDB, ICDE, ICDM, and CIKM. He has been serving as Associate Editor/Guest Editor/Editorial Board for Neural Networks (JCR Q1, CCF B, 中科院一区), Science China Information Sciences (JCR Q1, CCF A, 中科院一区), Data Science and Engineering (JCR Q1, 中科院一区), Journal of Computer Science and Technology (JCST, CCF B), Journal of Social Computing, ACM Transactions on Information Systems 2022-2023 (JCR Q1, CCF A, CORE A, 中科院一区), ACM Transactions on Intelligent Systems and Technology 2020-2021 (JCR Q1), Information Systems 2020-2021 (CORE A*), and World Wide Web 2020-2021 and 2017-2018 (CORE A, CCF B). Dr. Yin has also been attracting wide media coverage, such as The Australian, SBS Radio Interviews, UQ News, Sohu.com, Faculty News of EAIT, IEEE Computer Society, ACM Computing Reviews.

I am now looking for highly motivated Ph.D. students. The University of Queensland ranks in the top 50 as measured by the Performance Ranking of Scientific Papers for World Universities. The University also ranks 40 in the QS World University Rankings and 41 in the US News Best Global Universities Rankings. The University of Queensland is the best in Australia according to the Australian Financial Review (AFR), which has now ranked UQ in the #1 position for 2 consecutive years. Please find the following three PhD scholarships.

Latest News

  1. [20 May 2026] Our ARC Linkage Project 2025 "AI-Powered Design Co-Pilot for Reimagining Australian Single-Family Homes" has been successfully granted and funded.

  2. [16 May 2026] We have three research papers accepted by the top conference KDD 2026 Research Track (CORE A*, CCF A, Acceptance Rate ~18%).

  3. [12 May 2026] I have been recognised in 2026 Edition of Best Scientists in the field of Computer Science and ranked 42 in Australia on Research.com, a leading academic platform.

  4. [8 May 2026] Our research paper "Efficient Prompt Learning for Traffic Forecasting" has been accepted by VLDB Journal (CORE A*, CCF A)

  5. [3 April 2026] We have 3 research papers accepted by the top conference SIGIR 2026.

    • Prompt-Unknown Promotion Attacks against LLM-based Sequential Recommender Systems

    • ProMax: Exploring the Potential of LLM-derived Profiles with Distribution Shaping for Recommender Systems

    • ProEchoMem: Enhancing Long Video Understanding via Multi-Trace Probe-Echo Memory

  6. [27 March 2026] We have successfully secured the opportunity to host the top-tier conference ICDM 2027 in Brisbane.

  7. [24 Feb 2026] We have 3 research papers on ChatBI accepted by the top conferences ICLR 2026 (CORE A*, CCF A) and ICDE 2026 (CORE A*, CCF A).

  8. [21 Feb 2026] I’m pleased to join the Organizing Committee of the premier conference WSDM 2027 as the Conference Awards Co-Chair.

  9. [18 Feb 2026] I’m pleased to join the Organizing Committee of the data mining flagship conference ADMA 2026 as the PC Co-Chair.

  10. [5 Feb 2026] We are organizing a workshop "LLM-UP: LLM-powered User Profiling for Search and Recommendation" at SIGIR 2026.

  11. [26 January 2026] We have 3 papers accepted by the top conference ICLR 2026 (CORE A*).

  12. [20 January 2026] I was invited to serve as Area Chair in the top conference KDD 2026 (CORE A*, CCF A), IJCAI 2026 (CORE A*, CCF A), ARR-ACL 2026 (CORE A*, CCF A) and ICDM 2026 (CORE A*, CCF B).

  13. [14 January] We have two research papers accepted by the top conference WWW 2026 (CORE A*, CCF A). Congratulations to Xinyi and Hung.

  14. [13 January 2025] We have two research papers recognized as ESI Hot Papers and five research papers recognized as ESI Highly Cited Papers.

  15. [19 December 2025] I was invited to serve as Area Chair in the top conference SIGIR 2026 (CORE A*, CCF A) and senior PC member at the top conference ICMR 2026 (CORE A, CCF B).

  16. [9 December 2025] I have been recognized as 2025 ScholarGPS Highly Ranked Scholar (top 0.05% of all scholars), #3 in Data Mining, #8 in Information Engineering.

  17. [8 November 2025] Our research paper "SmartAgent: Chain-of-User-Thought for Embodied Personalized Agent in Cyber World" was accepted by the top conference AAAI 2026 (CCF A and CORE A*). Congratulations to Jiaqi.

  18. [4 November 2025] We have released the first survey on Reasoning-Aware Recommender Systems in the LLM Era.

  19. [28 October 2025] My ARC Discovery Project 2026 "Advancing Federated Learning for Unified Urban Spatio-Temporal Predictions" has been successfully granted and funded.

  20. [13 October 2025] I was invited to be Area Chair for ACL Rolling Review (ARR).

  21. [1 October 2025] I have been recognised in the Stanford/Elsevier Top 2% Scientists List Career Long (2022-2025) and Single Year (2020-2025).

Availability

Professor Hongzhi Yin is:
Available for supervision

Qualifications

  • Postgraduate Diploma, Peking University
  • Doctor of Philosophy, Peking University

Research interests

  • Structured Foundation Model

  • Spatial-temporal Prediction

  • LLM and ChatBI

  • Recommender System and User Modeling

  • Edge Machine Learning and Applications

  • Time Series and Sequence Mining and Prediction

  • Trustworthy Machine Learning and Applications

Research impacts

Prof. Yin is currently directing the Responsible Big Data Intelligence Lab (RBDI). RBDI Lab aims and strives to develop decentralized, on-device, and trustworthy (e.g., privacy-preserving, robust, explainable and fair) data mining and machine learning techniques with theoretical backbones to better discover actionable patterns and intelligence from large-scale, heterogeneous, networked, dynamic and sparse data. RBDI joins forces with other fields such as urban transportation, healthcare, agriculture, E-commerce and marketing to help solve societal, environmental and economic challenges facing humanity in pursuit of a sustainable future. His research has also attracted media coverage, such as The Australian, SBS, UQ News, Faculty News of EAIT, ACM Computing Reviews, 360 News.

Works

Search Professor Hongzhi Yin’s works on UQ eSpace

425 works between 2011 and 2026

21 - 40 of 425 works

2025

Journal Article

A data-driven scale-adaptive time-frequency convolutional network for long sequence time-series forecasting

Zhang, Zhiqiang, Wang, Weiqing, Zhou, Xin, Bai, Yu and Yin, Hongzhi (2025). A data-driven scale-adaptive time-frequency convolutional network for long sequence time-series forecasting. IEEE Transactions on Knowledge and Data Engineering, 37 (12), 6750-6764. doi: 10.1109/TKDE.2025.3619521

A data-driven scale-adaptive time-frequency convolutional network for long sequence time-series forecasting

2025

Journal Article

DecKG: decentralized collaborative learning with knowledge graph enhancement for POI recommendation

Zheng, Ruiqi, Qu, Liang, Ye, Guanhua, Chen, Tong, Shi, Yuhui and Yin, Hongzhi (2025). DecKG: decentralized collaborative learning with knowledge graph enhancement for POI recommendation. Information Sciences, 721 122570, 122570-721. doi: 10.1016/j.ins.2025.122570

DecKG: decentralized collaborative learning with knowledge graph enhancement for POI recommendation

2025

Journal Article

On-device recommender systems: a comprehensive survey

Yin, Hongzhi, Qu, Liang, Chen, Tong, Yuan, Wei, Zheng, Ruiqi, Long, Jing, Xia, Xin, Shi, Yuhui and Zhang, Chengqi (2025). On-device recommender systems: a comprehensive survey. Data Science and Engineering, 10 (4), 591-620. doi: 10.1007/s41019-025-00308-8

On-device recommender systems: a comprehensive survey

2025

Conference Publication

Harnessing large language models for Group POI recommendations

Long, Jing, Qu, Liang, Yu, Junliang, Chen, Tong, Nguyen, Quoc Viet Hung and Yin, Hongzhi (2025). Harnessing large language models for Group POI recommendations. 34th ACM International Conference on Information and Knowledge Management CIKM 2025, Seoul, Republic of Korea, 10-14 November 2025. New York, NY, United States: ACM. doi: 10.1145/3746252.3761018

Harnessing large language models for Group POI recommendations

2025

Conference Publication

NR-GCF: Graph Collaborative Filtering with Improved Noise Resistance

Chen, Yijun, Li, Bohan, Li, Yicong, Song, Lixiang, Wang, Haofen, Wu, Wenlong, Zhuo, Junnan and Yin, Hongzhi (2025). NR-GCF: Graph Collaborative Filtering with Improved Noise Resistance. 34th ACM International Conference on Information and Knowledge Management CIKM 2025, Seoul, Korea, 10 - 14 November 2025. New York, NY United States: Association for Computing Machinery. doi: 10.1145/3746252.3761342

NR-GCF: Graph Collaborative Filtering with Improved Noise Resistance

2025

Conference Publication

HGAurban: Heterogeneous Graph Autoencoding for Urban Spatial-Temporal Learning

Zhang, Qianru, Gao, Xinyi, Wang, Haixin, Huang, Dong, Yiu, Siu-Ming and Yin, Hongzhi (2025). HGAurban: Heterogeneous Graph Autoencoding for Urban Spatial-Temporal Learning. 34th ACM International Conference on Information and Knowledge Management CIKM 2025, Seoul, Korea, 10 - 14 November 2025. New York, NY United States: Association for Computing Machinery. doi: 10.1145/3746252.3761383

HGAurban: Heterogeneous Graph Autoencoding for Urban Spatial-Temporal Learning

2025

Conference Publication

Efficient multimodal streaming recommendation via Expandable Side Mixture-of-Experts

Qu, Yunke, Qu, Liang, Chen, Tong, Nguyen, Quoc Viet Hung and Yin, Hongzhi (2025). Efficient multimodal streaming recommendation via Expandable Side Mixture-of-Experts. CIKM '25: The 34th ACM International Conference on Information and Knowledge Management, Seoul, South Korea, 10-14 November 2025. New York, United States: Association for Computing Machinery. doi: 10.1145/3746252.3761390

Efficient multimodal streaming recommendation via Expandable Side Mixture-of-Experts

2025

Journal Article

Teaching MLPs to master heterogeneous graph-structured knowledge for efficient and accurate inference

Liu, Yunhui, Gao, Xinyi, He, Tieke, Zhao, Jianhua and Yin, Hongzhi (2025). Teaching MLPs to master heterogeneous graph-structured knowledge for efficient and accurate inference. IEEE Transactions on Knowledge and Data Engineering (10), 6189-6201. doi: 10.1109/tkde.2025.3589596

Teaching MLPs to master heterogeneous graph-structured knowledge for efficient and accurate inference

2025

Journal Article

Enhancing language models with commonsense knowledge for multi-turn response selection

Wang, Yuandong, Ren, Xuhui, Chen, Tong, Yin, Hongzhi and Hung, Nguyen Quoc Viet (2025). Enhancing language models with commonsense knowledge for multi-turn response selection. International Journal of Machine Learning and Cybernetics, 16 (12), 10421-10441. doi: 10.1007/s13042-025-02804-9

Enhancing language models with commonsense knowledge for multi-turn response selection

2025

Journal Article

FELLAS: enhancing federated sequential recommendation with LLM as external services

Yuan, Wei, Yang, Chaoqun, Ye, Guanhua, Chen, Tong, Hung, Nguyen Quoc Viet and Yin, Hongzhi (2025). FELLAS: enhancing federated sequential recommendation with LLM as external services. ACM Transactions on Information Systems, 43 (6) 144, 1-24. doi: 10.1145/3709138

FELLAS: enhancing federated sequential recommendation with LLM as external services

2025

Journal Article

BEOL-compatible annealing-free HfxZr1-xO2 ferroelectric device and investigation of cycle-dependent evolution mechanisms

Liu, Yongkai, Yuan, Aolin, Song, Yifan, Yuan, Ruihong, Liu, Pei, Li, Zhenhai, Xu, Ze, Xu, Kangli, Yu, Jiajie, Meng, Jialin, Wang, Chen, Zhu, Hao, Sun, Qingqing, Zhang, David Wei, Wang, Tianyu and Chen, Lin (2025). BEOL-compatible annealing-free HfxZr1-xO2 ferroelectric device and investigation of cycle-dependent evolution mechanisms. IEEE Transactions on Electron Devices, 72 (10), 5422-5427. doi: 10.1109/TED.2025.3601559

BEOL-compatible annealing-free HfxZr1-xO2 ferroelectric device and investigation of cycle-dependent evolution mechanisms

2025

Journal Article

Knowledge enhancement and temporal aware for multi-behavior contrastive recommendation

Xuan, Hongrui, Li, Bohan, Wu, Wenlong, Liu, Yi and Yin, Hongzhi (2025). Knowledge enhancement and temporal aware for multi-behavior contrastive recommendation. ACM Transactions on Intelligent Systems and Technology, 16 (5) 102, 1-23. doi: 10.1145/3735512

Knowledge enhancement and temporal aware for multi-behavior contrastive recommendation

2025

Journal Article

HGDNet: de-noised review-based rating prediction using hierarchical gating and discriminative networks

Ma, Jingwei, Wen, Jiahui, Zhu, Lei, Zhong, Mingyang, Xu, Yang, Guo, Lei and Yin, Hongzhi (2025). HGDNet: de-noised review-based rating prediction using hierarchical gating and discriminative networks. ACM Transactions on Information Systems, 43 (5) 140. doi: 10.1145/3746282

HGDNet: de-noised review-based rating prediction using hierarchical gating and discriminative networks

2025

Conference Publication

Data watermarking for sequential recommender systems

Zhang, Sixiao, Long, Cheng, Yuan, Wei, Chen, Hongxu and Yin, Hongzhi (2025). Data watermarking for sequential recommender systems. The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Toronto, Canada, 3-7 August 2025. New York, NY USA: Association for Computing Machinery. doi: 10.1145/3711896.3736903

Data watermarking for sequential recommender systems

2025

Conference Publication

Multi-task offline reinforcement learning for online advertising in recommender systems

Liu, Langming, Wang, Wanyu, Zhang, Chi, Li, Bo, Yin, Hongzhi, Wei, Xuetao, Su, Wenbo, Zheng, Bo and Zhao, Xiangyu (2025). Multi-task offline reinforcement learning for online advertising in recommender systems. The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Toronto, Canada, 3-7 August 2025. New York, NY USA: Association for Computing Machinery. doi: 10.1145/3711896.3737250

Multi-task offline reinforcement learning for online advertising in recommender systems

2025

Conference Publication

FindRec: Stein-guided entropic flow for multi-modal sequential recommendation

Wang, Maolin, Xiao, Yutian, Wang, Binhao, Zhang, Sheng, Ye, Shanshan, Wang, Wanyu, Yin, Hongzhi, Guo, Ruocheng and Xu, Zenglin (2025). FindRec: Stein-guided entropic flow for multi-modal sequential recommendation. The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Toronto, Canada, 3-7 August 2025. New York, NY USA: Association for Computing Machinery. doi: 10.1145/3711896.3736968

FindRec: Stein-guided entropic flow for multi-modal sequential recommendation

2025

Conference Publication

Contrastive graph condensation: advancing data versatility through self-supervised learning

Gao, Xinyi, Li, Yayong, Chen, Tong, Ye, Guanhua, Zhang, Wentao and Yin, Hongzhi (2025). Contrastive graph condensation: advancing data versatility through self-supervised learning. The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Toronto, Canada, 3-7 August 2025. New York, NY USA: Association for Computing Machinery. doi: 10.1145/3711896.3736892

Contrastive graph condensation: advancing data versatility through self-supervised learning

2025

Journal Article

RobGC: towards robust graph condensation

Gao, Xinyi, Yin, Hongzhi, Chen, Tong, Ye, Guanhua, Zhang, Wentao and Cui, Bin (2025). RobGC: towards robust graph condensation. IEEE Transactions on Knowledge and Data Engineering, 37 (8), 4791-4804. doi: 10.1109/tkde.2025.3569629

RobGC: towards robust graph condensation

2025

Journal Article

A survey of machine unlearning

Nguyen, Thanh Tam, Huynh, Thanh Trung, Ren, Zhao, Nguyen, Phi Le, Liew, Alan Wee-Chung, Yin, Hongzhi and Nguyen, Quoc Viet Hung (2025). A survey of machine unlearning. ACM Transactions on Intelligent Systems and Technology, 16 (5) 3749987, 1-46. doi: 10.1145/3749987

A survey of machine unlearning

2025

Conference Publication

Progressive Generalization Risk Reduction for Data-Efficient Causal Effect Estimation

Wen, Hechuan, Chen, Tong, Ye, Guanhua, Chai, Li Kheng, Sadiq, Shazia and Yin, Hongzhi (2025). Progressive Generalization Risk Reduction for Data-Efficient Causal Effect Estimation. KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Toronto, Canada, 3 - 7 August 2025. New York, NY United States: Association for Computing Machinery. doi: 10.1145/3690624.3709305

Progressive Generalization Risk Reduction for Data-Efficient Causal Effect Estimation

Funding

Current funding

  • 2026 - 2029
    Advancing Federated Learning for Unified Urban Spatio-Temporal Predictions
    ARC Discovery Projects
    Open grant
  • 2025 - 2028
    Revolutionise Australian Strata Management with Large Language Models
    ARC Linkage Projects
    Open grant
  • 2025 - 2028
    Building an Aussie Information Recommendation System You Can Trust
    ARC Linkage Projects
    Open grant
  • 2024 - 2027
    Privacy-Aware and Personalised Explanation Overlays for Recommender Systems (ARC Discovery Project administered by Griffith University)
    ARC Discovery Projects
    Open grant
  • 2022 - 2026
    Decentralised Collaborative Predictive Analytics on Personal Smart Devices
    ARC Future Fellowships
    Open grant
  • 2021 - 2026
    ARC Training Centre for Information Resilience
    ARC Industrial Transformation Training Centres
    Open grant

Past funding

  • 2022 - 2023
    A Secured Smart Sensing and Industry Analytics Facility for Industry 4.0 (ARC LIEF application led by University of Technology Sydney)
    University of Technology Sydney
    Open grant
  • 2020 - 2021
    Developing a Privacy-Preserving and Energy-Efficient Mobile Recommender System Architecture
    UQ Foundation Research Excellence Awards
    Open grant
  • 2019 - 2024
    Challenging Big Data for Scalable, Robust and Real-time Recommendations
    ARC Discovery Projects
    Open grant
  • 2017 - 2020
    Monitoring Social Events for User Online Behaviour Analytics
    ARC Discovery Projects
    Open grant
  • 2016 - 2018
    Mobile User Modeling for Intelligent Recommendation
    ARC Discovery Early Career Researcher Award
    Open grant

Supervision

Availability

Professor Hongzhi Yin is:
Available for supervision

Looking for a supervisor? Read our advice on how to choose a supervisor.

Available projects

  • Building an Trustworthy Information Recommendation System

    Build a trustworthy information recommender system by spearheading the design and development of cutting-edge LLM4Rec techniques, misinformation filters, and privacy protection mechanisms.

    This Earmarked Scholarship project is aligned with a recently awarded Category 1 research grant. It offers you the opportunity to work with leading researchers and contribute to large projects of national significance.

Supervision history

Current supervision

  • Doctor Philosophy

    Revolutionise Australian Strata Management with Large Language Models

    Principal Advisor

    Other advisors: Associate Professor Rocky Chen

  • Doctor Philosophy

    Chain-of-User-Thought for Personalized Agent in Cyber World

    Principal Advisor

  • Doctor Philosophy

    Decentralised Collaborative Predictive Analytics on Personal Smart Devices

    Principal Advisor

    Other advisors: Associate Professor Rocky Chen

  • Doctor Philosophy

    LLM-enhanced Recommender System

    Principal Advisor

    Other advisors: Associate Professor Rocky Chen

  • Doctor Philosophy

    Reliable Multimodal Recommender Systems

    Principal Advisor

    Other advisors: Associate Professor Rocky Chen

  • Doctor Philosophy

    Scalable and Lightweight On-Device Recommender Systems

    Associate Advisor

    Other advisors: Associate Professor Rocky Chen

  • Doctor Philosophy

    Robustness Verification of Neural Network

    Associate Advisor

    Other advisors: Dr Naipeng Dong

  • Doctor Philosophy

    Integrated high-throughput material synthesis and characterisation system

    Associate Advisor

    Other advisors: Associate Professor Jingwei Hou

  • Doctor Philosophy

    Scalable and Lightweight On-Device Recommender Systems

    Associate Advisor

    Other advisors: Associate Professor Rocky Chen

  • Doctor Philosophy

    Scalable and Generalizable Graph Neural Networks

    Associate Advisor

    Other advisors: Associate Professor Rocky Chen

  • Doctor Philosophy

    Sustainable On-Device Recommender Systems

    Associate Advisor

    Other advisors: Associate Professor Rocky Chen

  • Doctor Philosophy

    Lightweight Graph Neural Networks for Recommendation

    Associate Advisor

    Other advisors: Associate Professor Rocky Chen

Completed supervision

Media

Enquiries

For media enquiries about Professor Hongzhi Yin's areas of expertise, story ideas and help finding experts, contact our Media team:

communications@uq.edu.au