Skip to menu Skip to content Skip to footer
Dr Junliang Yu
Dr

Junliang Yu

Email: 

Overview

Background

Junliang Yu is currently an ARC DECRA Fellow with the Data Science discipline at The University of Queensland (UQ). Previously, he worked as a postdoctoral research fellow with Prof. Shazia Sadiq. He completed his PhD degree at UQ in 2023 under the supervision of Prof. Hongzhi Yin. Before his time at UQ, he earned his M.Sc. and B.E. degrees at Chongqing University, where he was supervised by Prof. Min Gao.

Availability

Dr Junliang Yu is:
Available for supervision

Qualifications

  • Bachelor of Software Engineering, Chongqing University
  • Masters (Research) of Software Engineering, Chongqing University
  • Doctor of Philosophy of Data Science, The University of Queensland

Research interests

  • Self-Supervised Learning

  • Recommender Systems

  • Tiny Machine Learning

  • Data-Centric AI

Research impacts

He is dedicated to conducting influential and reproducible research. His work has received over 3,600 citations as of December 2024, with five of his conference papers being recognized as The Most Influential Papers by Paper Digest and three of my journal papers being recognized as ESI Hot / Highly Cited Papers in his research areas. He is actively involved in the open-source community and have developed two popular recommender system frameworks, QRec and SELFRec, which have together garnered over 2,000 stars.

Works

Search Professor Junliang Yu’s works on UQ eSpace

50 works between 2017 and 2025

1 - 20 of 50 works

Featured

2022

Conference Publication

Are Graph Augmentations Necessary? : Simple Graph Contrastive Learning for Recommendation

Yu, Junliang, Yin, Hongzhi, Xia, Xin, Chen, Tong, Cui, Lizhen and Nguyen, Quoc Viet Hung (2022). Are Graph Augmentations Necessary? : Simple Graph Contrastive Learning for Recommendation. SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, 11 - 15 July 2022. New York, NY United States: Association for Computing Machinery. doi: 10.1145/3477495.3531937

Are Graph Augmentations Necessary? : Simple Graph Contrastive Learning for Recommendation

Featured

2021

Conference Publication

Self-supervised multi-channel hypergraph convolutional network for social recommendation

Yu, Junliang, Yin, Hongzhi, Li, Jundong, Wang, Qinyong, Hung, Nguyen Quoc Viet and Zhang, Xiangliang (2021). Self-supervised multi-channel hypergraph convolutional network for social recommendation. WWW '21: Proceedings of the Web Conference 2021, Ljubljana, Slovenia, 19-23 April 2021. New York, NY USA: Association for Computing Machinery. doi: 10.1145/3442381.3449844

Self-supervised multi-channel hypergraph convolutional network for social recommendation

Featured

2018

Conference Publication

Adaptive implicit friends identification over heterogeneous network for social recommendation

Yu, Junliang, Gao, Min, Li, Jundong, Yin, Hongzhi and Liu, Huan (2018). Adaptive implicit friends identification over heterogeneous network for social recommendation. 27th ACM International Conference on Information and Knowledge Management, CIKM 2018, Torino, Italy, 22-26 October 2018. New York, NY, United States: Association for Computing Machinery (ACM). doi: 10.1145/3269206.3271725

Adaptive implicit friends identification over heterogeneous network for social recommendation

2025

Conference Publication

BiasNavi: LLM-Empowered Data Bias Management

Yu, Junliang, Huynh, Jay Thai Duong, Fan, Shaoyang, Demartini, Gianluca, Chen, Tong, Yin, Hongzhi and Sadiq, Shazia (2025). BiasNavi: LLM-Empowered Data Bias Management. New York, NY, USA: ACM. doi: 10.1145/3701716.3715169

BiasNavi: LLM-Empowered Data Bias Management

2025

Conference Publication

Graph Condensation: Foundations, Methods and Prospects

Yin, Hongzhi, Gao, Xinyi, Yu, Junliang, Qiu, Ruihong, Chen, Tong, Nguyen, Quoc Viet Hung and Huang, Zi (2025). Graph Condensation: Foundations, Methods and Prospects. New York, NY, USA: ACM. doi: 10.1145/3701716.3715862

Graph Condensation: Foundations, Methods and Prospects

2025

Conference Publication

Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partition

Gao, Xinyi, Ye, Guanhua, Chen, Tong, Zhang, Wentao, Yu, Junliang and Yin, Hongzhi (2025). Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partition. WWW '25: The ACM Web Conference 2025, Sydney, NSW Australia, 28 April - 2 May 2025. New York, NY United States: Association for Computing Machinery. doi: 10.1145/3696410.3714916

Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partition

2025

Journal Article

Graph condensation: a survey

Gao, Xinyi, Yu, Junliang, Chen, Tong, Ye, Guanhua, Zhang, Wentao and Yin, Hongzhi (2025). Graph condensation: a survey. IEEE Transactions on Knowledge and Data Engineering, 37 (4), 1819-1837. doi: 10.1109/tkde.2025.3535877

Graph condensation: a survey

2025

Conference Publication

Towards Secure and Robust Recommender Systems: A Data-Centric Perspective

Wang, Zongwei, Yu, Junliang, Chen, Tong, Yin, Hongzhi, Sadiq, Shazia and Gao, Min (2025). Towards Secure and Robust Recommender Systems: A Data-Centric Perspective. 18th International Conference on Web Search and Data Mining-WSDM, Hannover Germany, Mar 10-14, 2025. New York, NY, USA: ACM. doi: 10.1145/3701551.3703484

Towards Secure and Robust Recommender Systems: A Data-Centric Perspective

2025

Journal Article

A Survey on Point-of-Interest Recommendation: Models, Architectures, and Security

Zhang, Qianru, Yang, Peng, Yu, Junliang, Wang, Haixin, He, Xingwei, Yiu, Siu-Ming and Yin, Hongzhi (2025). A Survey on Point-of-Interest Recommendation: Models, Architectures, and Security. IEEE Transactions on Knowledge and Data Engineering, PP (99), 1-20. doi: 10.1109/tkde.2025.3551292

A Survey on Point-of-Interest Recommendation: Models, Architectures, and Security

2024

Conference Publication

Unveiling vulnerabilities of contrastive recommender systems to poisoning attacks

Wang, Zongwei, Yu, Junliang, Gao, Min, Yin, Hongzhi, Cui, Bin and Sadiq, Shazia (2024). Unveiling vulnerabilities of contrastive recommender systems to poisoning attacks. 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Barcelona, Spain, 25-29 August 2024. New York, NY, United States: ACM. doi: 10.1145/3637528.3671795

Unveiling vulnerabilities of contrastive recommender systems to poisoning attacks

2024

Conference Publication

Consistency and discrepancy-based contrastive tripartite graph learning for recommendations

Guo, Linxin, Zhu, Yaochen, Gao, Min, Tao, Yinghui, Yu, Junliang and Chen, Chen (2024). Consistency and discrepancy-based contrastive tripartite graph learning for recommendations. 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Barcelona, Spain, 25-29 August 2024. New York, NY, United States: ACM. doi: 10.1145/3637528.3672056

Consistency and discrepancy-based contrastive tripartite graph learning for recommendations

2024

Conference Publication

Prompt-enhanced federated content representation learning for cross-domain recommendation

Guo, Lei, Lu, Ziang, Yu, Junliang, Nguyen, Quoc Viet Hung and Yin, Hongzhi (2024). Prompt-enhanced federated content representation learning for cross-domain recommendation. 33rd ACM Web Conference, WWW 2024, Singapore, 13 May 2024. New York, NY United States: Association for Computing Machinery. doi: 10.1145/3589334.3645337

Prompt-enhanced federated content representation learning for cross-domain recommendation

2024

Conference Publication

Accelerating scalable graph neural network inference with node-adaptive propagation

Gao, Xinyi, Zhang, Wentao, Yu, Junliang, Shao, Yingxia, Nguyen, Quoc Viet Hung, Cui, Bin and Yin, Hongzhi (2024). Accelerating scalable graph neural network inference with node-adaptive propagation. 2024 IEEE 40th International Conference on Data Engineering (ICDE), Utrecht, Netherlands, 13-16 May 2024. Piscataway, NJ, United States: IEEE. doi: 10.1109/icde60146.2024.00236

Accelerating scalable graph neural network inference with node-adaptive propagation

2024

Conference Publication

Motif-based prompt learning for universal cross-domain recommendation

Hao, Bowen, Yang, Chaoqun, Guo, Lei, Yu, Junliang and Yin, Hongzhi (2024). Motif-based prompt learning for universal cross-domain recommendation. 17th ACM International Conference on Web Search and Data Mining (WSDM), Merida, Mexico, 4-8 March 2024. New York, NY United States: Association for Computing Machinery. doi: 10.1145/3616855.3635754

Motif-based prompt learning for universal cross-domain recommendation

2024

Journal Article

XSimGCL: towards extremely simple graph contrastive learning for recommendation

Yu, Junliang, Xia, Xin, Chen, Tong, Cui, Lizhen, Hung, Nguyen Quoc Viet and Yin, Hongzhi (2024). XSimGCL: towards extremely simple graph contrastive learning for recommendation. IEEE Transactions on Knowledge and Data Engineering, 36 (2), 913-926. doi: 10.1109/tkde.2023.3288135

XSimGCL: towards extremely simple graph contrastive learning for recommendation

2024

Journal Article

Self-supervised learning for recommender systems: a survey

Yu, Junliang, Yin, Hongzhi, Xia, Xin, Chen, Tong, Li, Jundong and Huang, Zi (2024). Self-supervised learning for recommender systems: a survey. IEEE Transactions on Knowledge and Data Engineering, 36 (1), 335-355. doi: 10.1109/tkde.2023.3282907

Self-supervised learning for recommender systems: a survey

2023

Conference Publication

Towards communication-efficient model updating for on-device session-based recommendation

Xia, Xin, Yu, Junliang, Xu, Guandong and Yin, Hongzhi (2023). Towards communication-efficient model updating for on-device session-based recommendation. 32nd ACM International Conference on Information and Knowledge Management (CIKM), Birmingham, United Kingdom, 21-25 October 2023. New York, NY, United States: ACM. doi: 10.1145/3583780.3615088

Towards communication-efficient model updating for on-device session-based recommendation

2023

Conference Publication

Semantic-aware node synthesis for imbalanced heterogeneous information networks

Gao, Xinyi, Zhang, Wentao, Chen, Tong, Yu, Junliang, Nguyen, Hung Quoc Viet and Yin, Hongzhi (2023). Semantic-aware node synthesis for imbalanced heterogeneous information networks. 32nd ACM International Conference on Information and Knowledge Management, Birmingham, United Kingdom, 21–25 October 2023. New York, NY, United States: Association for Computing Machinery. doi: 10.1145/3583780.3615055

Semantic-aware node synthesis for imbalanced heterogeneous information networks

2023

Journal Article

Predictive and contrastive: dual-auxiliary learning for recommendation

Tao, Yinghui, Gao, Min, Yu, Junliang, Wang, Zongwei, Xiong, Qingyu and Wang, Xu (2023). Predictive and contrastive: dual-auxiliary learning for recommendation. IEEE Transactions on Computational Social Systems, 10 (5), 2254-2265. doi: 10.1109/TCSS.2022.3185714

Predictive and contrastive: dual-auxiliary learning for recommendation

2023

Journal Article

Efficient on-device session-based recommendation

Xia, Xin, Yu, Junliang, Wang, Qinyong, Yang, Chaoqun, Hung, Nguyen Quoc Viet and Yin, Hongzhi (2023). Efficient on-device session-based recommendation. ACM Transactions on Information Systems, 41 (4) 102, 1-24. doi: 10.1145/3580364

Efficient on-device session-based recommendation

Funding

Current funding

  • 2025 - 2028
    Distilling Data for Cost-Efficient Recommender Systems
    ARC Discovery Early Career Researcher Award
    Open grant

Supervision

Availability

Dr Junliang Yu is:
Available for supervision

Before you email them, read our advice on how to contact a supervisor.

Supervision history

Current supervision

  • Doctor Philosophy

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

    Associate Advisor

    Other advisors: Professor Hongzhi Yin

  • Doctor Philosophy

    Scalable and Lightweight On-Device Recommender Systems

    Associate Advisor

    Other advisors: Professor Hongzhi Yin, Dr Rocky Chen

Media

Enquiries

For media enquiries about Dr Junliang Yu's areas of expertise, story ideas and help finding experts, contact our Media team:

communications@uq.edu.au