Profile of Prof XU, Guandong 徐貫東 - The Education University of Hong Kong


Chair Professor	Department of Mathematics and Information Technology
Director	University Research Facility of Data Science and Artificial Intelligence
Director	Centre for Learning, Teaching and Technology

Contact

ORCiD

0000-0003-4493-6663

Phone

(852) 2948 8818

Fax

(852) 2948 7046

gdxu@eduhk.hk

Address

10 Lo Ping Road, Tai Po, New Territories, Hong Kong

Website

https://pappl.eduhk.hk/rich/web/person.xhtml?pid=308319&name=XU, Guandong

Scopus ID

8987733300

SDGs

3 - Good Health and Well-Being
4 - Quality Education
5 - Gender Equality
9 - Industry, Innovation and Infrastructure
10 - Reduced Inequality
11 - Sustainable Cities and Communities

Research Outputs


Scholarly Books, Monographs and Chapters Xu, G., & Fang, B. (2025). The Application of MDATA Cognitive Model in Network Public Opinion Analysis. In, Y. Jia, Z. Gu, A. Li, & B. Fang (Eds.), MDATA Cognitive Model: Theory and Applications (pp. 181-207). Singapore: Springer. https://doi.org/10.1007/978-981-96-3528-3_7
Journal Publications Deng, J., Shi, K., Wu, Z., Huo, H., Wang, D., & Xu, G. (2026). Enabling collaborative parametric knowledge calibration for retrieval-augmented Vision Question Answering. Knowledge-Based Systems, 346, Article 116157. https://doi.org/10.1016/j.knosys.2026.116157 Deng, J., Wu, Z., Huo, H., & Xu, G. (2026). A comprehensive survey of knowledge-based visual question answering systems: The lifecycle of knowledge in visual reasoning task. IEEE Transactions on Knowledge and Data Engineering, Pre-print, 1-20. https://doi.ieeecomputersociety.org/10.1109/TKDE.2026.3699946 Guo, L., Wu, S., Lu, D., Gao, L., & Xu, G. (2026). Dual-channel time-aware graph attention network for session-based recommendation. Information Sciences, 741, Article 123289. https://doi.org/10.1016/j.ins.2026.123289 Barajeeh, B., Yankouskaya, A., AlShakhsi, S., Ho, C.S.M., Xu, G., & Ali, R. (2026). Developing and validating the Arabic version of the attitudes toward large language models scale. SN Computer Science, 7, Article 434. https://doi.org/10.1007/s42979-026-04855-3 Feng Zhao, Kangzheng Liu, Yu Yang, & Guandong Xu (2026). Cog-RMH: Cognition-based Recalling Multiview history for event forecasting in temporal knowledge graph. IEEE Transactions on Knowledge and Data Engineering, 14(8). https://doi.org/10.1109/TKDE.2026.3689542 Gu, M., Liu, L., Lu, X., Xu, G., Sun, X. & Lu, J. (2026). Vul2Vec: Semantic-enhanced similarity computing for effective vulnerability retrieval. Web Intelligence, OnlineFirst, 1-15. https://doi.org/10.1177/24056456261451035 Kangzheng Liu, Feng Zhao, Yu Yang, & Guandong Xu (2026). Hyperbolic dual-attentive evolution of heterogeneous deep hierarchy for temporal knowledge graph reasoning. IEEE Transactions on Knowledge and Data Engineering. https://doi.org/10.1109/TKDE.2026.3694589 Alsuhaibani, A., Alalawi, A., Razzak, I., Jameel, S., Wang, X., & Xu, G. (2026). Cluster-SCP: Similarity and contrastive learning to enhance pseudo labels for fine tuning under few labels. World Wide Web, 29, Article 28. https://doi.org/10.1007/s11280-026-01415-w Chen, Y., Shi, K., Wu, Z., Chen, J., Wang, X., McAuley, J., Xu, G., & Yu, S. (2026). A temporally disentangled contrastive diffusion model for spatiotemporal imputation. CAAI Transactions on Intelligence Technology, 11(2), 548-563. https://doi.org/10.1049/cit2.70085 Sun, X., Shi, K., Lin, Q., Li, Q., & Xu, G. (2026). Context-aware toxicity-adaptive sampling for affective language generation. IEEE Transactions on Affective Computing, Early Access, 1-12. https://doi.org/10.1109/TAFFC.2026.3685346 Liang, J., Yang, H., Zhao, X., Yu, Z., Xu, G., Wang, W., & Yang, K. (2026). Democratic recommendation with user and item representatives produced by graph condensation. IEEE Transactions on Knowledge and Data Engineering, 38(5), 2670-2686. https://doi.org/10.1109/TKDE.2026.3669777 Ma, S., Wu, S., Zeng, Y., Shi, K., & Xu, G. (2026). Multi-modal dual attention graph contrastive learning for recommendation. Knowledge-Based Systems, 337, Article 115404. https://doi.org/10.1016/j.knosys.2026.115404 Zhou, H., Lin, X., Cao, Y., Zhu, S., Jia, R., Zhao, X., Xu, G., & Guo, L. (2026). D2TCDR: Disentangled diffusion-based transfer for Cross-Domain Recommendation. ACM Transactions on Information Systems, 44(3), Article 68. https://doi.org/10.1145/3795793 Chen, Y., Cao, J., Wang, Y., Wu, J., Xu, G., Chen, H., Tao, H., & Vuković, D.B. (2026). Diffusion contrastive learning model for multi-behavior recommendation. IEEE Transactions on Big Data, Early Access, Article Online. https://doi.org/10.1109/TBDATA.2026.3668649 Hu, K., Li, L., Shi, K., Tang, S., Xie, H., Yan, R., & Xu, G. (2026). Quantitative reflection for mental state analysis via aspect sentiment triplet extraction. IEEE Transactions on Affective Computing, Early Access, 1-15, Article Online. https://doi.org/10.1109/TAFFC.2026.3663142 Yang, H., Chen, H., Zhao, X., Zhang, S., Sun, X., Li, Q., Yin, H., & Xu, G. (2026). Generating compressed counterfactual hard negative samples for graph contrastive learning. CAAI Transactions on Intelligence Technology, Early View, Article Online. https://doi.org/10.1049/cit2.70102 Yankouskaya, A., Almourad, M.B., Liebherr, M., Beyahi, F., Xu, G., & Ali, R. (2026). Who lets AI take over? Cross-national variation in willingness to delegate socially important roles to artificial intelligence. AI and Society, Online, Article Online. https://doi.org/10.1007/s00146-026-02858-5 Lai, W., Xie, H., Xu, G., & Li, Q. (2026). Multi-task learning with LLMs for implicit sentiment analysis: Data-level and task-level automatic weight learning. IEEE Transactions on Knowledge and Data Engineering, 38(1), 506-517. https://doi.org/10.1109/TKDE.2025.3623941 Liu, D., Wei, Z., Maurer U., Chung, K. K. H., Datu, J. A. D., Fern-Pollak, L., Wydell, T., Tso, W. W.-Y., Sun, F., Luo, L., Wang, L.-C., Yum, Y. N., Xu, G., & Li, S. (2026). Profiling Chinese children with symptoms of SpLD, ADHD, or ASD: a transdiagnostic and biopsychosocial study. BMC Psychiatry, 26(114), .-.. https://doi.org/10.1186/s12888-025-07754-8 SDGs infomation: 3 - Good Health and Well-Being, 4 - Quality Education, 10 - Reduced Inequality Jin, J., Hong, Y., Xu, G., Zhang, J., Tang, J., & Wang, H. (2025). An event-centric framework for predicting crime hotspots with flexible time intervals. IEEE Transactions on Knowledge and Data Engineering, 37(12), 6902-6915. https://doi.org/10.1109/TKDE.2025.3618389 Lu, D., Wu, S., Zhang, H., Xu, G., & Han, Q. (2025). Causal cascading convolution networks for multi-behavior sequential recommendation. Information Sciences, 720, Article 122484. https://doi.org/10.1016/j.ins.2025.122484 Li, Z., Yang, C., Zhang, T., Chen, Y., Wang, X., Xu, G., & Dong, D. (2025). Listwise preference alignment optimization for tail item recommendation. IEEE Transactions on Computational Social Systems, Early Access, 1-14, Article Online. https://doi.org/10.1109/TCSS.2025.3626598 Yu, D., Li, Q., Huang, S., Cao, J., & Xu, G. (2025). Large language models meet causal inference: Semantic-rich dual propensity score for sequential recommendation. IEEE Transactions on Knowledge and Data Engineering, 37(11), 6494-6505. https://doi.org/10.1109/TKDE.2025.3606149 Chen, Y., Cao, J., Wang, Y., Wu, J., Chen, H., & Xu, G. (2025). Causal variational inference for Deconfounded multi-behavior recommendation. ACM Transactions on Information Systems, 43(6), Article 151. https://doi.org/10.1145/3745023 Huang, S., Li, Q., Yang, H., Yu, D., Li, Q., & Xu, G. (2025). Causal time-aware news recommendations with large language models. ACM Transactions on Information Systems, 43(6), Article 147. https://doi.org/10.1145/3729422 Wu, Z., Lin, G., Liu, H., Xie, J., Xu, G., Chen, E., & Li, G. (2025). How to protect of reader preference privacy in mobile book information services: A technical method. Journal of Data and Information Quality, 17(3), Article 13. https://doi.org/10.1145/3688395 Yu, D., Li, Q., Huo, H., & Xu, G. (2025). Breaking the loop: Causal learning to mitigate echo chambers in social networks. ACM Transactions on Information Systems, 43(6), Article 163. https://doi.org/10.1145/3757738 Chen, Y., Li, Z., Yang, C., Wang, X., & Xu, G. (2025). Large language models are few-shot multivariate time series classifiers. Data Mining and Knowledge Discovery, 39, Article 66. https://doi.org/10.1007/s10618-025-01145-z Tang, J., Gu, H., Vuković, D.B., Xu, G., Wang, Y., Tao, H., & Cao, J. (2025). Fraud detection in multi-relation graph: Contrastive learning on feature and structural levels. Neurocomputing, 637, Article 130063. https://doi.org/10.1016/j.neucom.2025.130063 Wang, D., Guo, G., Ouyang, T., Yu, D., Zhang, H., Li, B., Jiang, R., Xu, G., & Deng, S. (2025). A Lightweight Spatio-Temporal Neural Network With Sampling-Based Time Series Decomposition for Traffic Forecasting. IEEE Transactions on Intelligent Transportation Systems, 26(6), 8682-8693. https://doi.org/10.1109/TITS.2025.3552010 Sun, X., Shi, K., Tang, H., Wang, D., Xu, G. & Li, Q. (2025). Educating Language Models as Promoters: Multi-aspect Instruction Alignment with Self-augmentation. IEEE Transactions on Knowledge and Data Engineering, 37(8), 4564-4577. https://doi.org/10.1109/TKDE.2025.3569585 Tang, H., Sun, X., Wu, S., Cui, Z., Xu, G., & Li, Q. (2025). DyBooster: Leveraging Large Language Model as Booster for Dynamic Recommendation. Expert Systems with Applications, 286, Article 128080. https://doi.org/10.1016/j.eswa.2025.128080 Tang, H., Wu, S., Cui, Z., Li, Y., Xu, G., & Li, Q. (2025). Model-Agnostic Dual-Side Online Fairness Learning for Dynamic Recommendation. IEEE Transactions on Knowledge and Data Engineering, 37(5), 2727-2742. https://doi.org/10.1109/TKDE.2025.3544510 Wang, D., Yao, H., Yu, D., Song, S., Weng, H., Xu, G., & Deng, S. (2025). Graph Intention Embedding Neural Network for Tag-aware Recommendation. Neural Networks, 184, Article 107062. https://doi.org/10.1016/j.neunet.2024.107062 Wang, Y., Xu, G., Cao, J., Chen, Y., & Wu, J. (2025). Does Digital Literacy Affect Farmers' Adoption of Agricultural Social Services? An Empirical Study Based on China Land Economic Survey Data. PLoS One, 20(4), Article e0320318. https://doi.org/10.1371/journal.pone.0320318 Yang, C., Chen, Y., Li, Z., Wang, X., Shi, K., Yao, L., Xu, G., & Guo, Z. (2025). Deep Multimodal Learning for Time Series Analysis in Social Computing: A Survey. International Journal of Multimedia Information Retrieval, 14(15), Article 15. https://doi.org/10.1007/s13735-025-00363-x Yu, D., Guo, G., Wang, D., Ouyang, T., Wan, F., Liu, J., Xu, G., & Deng, S. (2025). Dynamic Spatial-temporal Graph Convolution Network for e-Bike Traffic Flow Forecasting. IEEE Transactions on Vehicular Technology, 74(4), 5453-5466. https://doi.org/10.1109/TVT.2024.3508021 Li, Q., Wang, Z., Xia, H., Li, G., Cao, Y., Yao, L., & Xu, G. (2025). HOT-GAN: Hilbert Optimal Transport for Generative Adversarial Network. IEEE Transactions on Neural Networks and Learning Systems, 36(3), 4371-4384. https://doi.org/10.1109/TNNLS.2024.3370617 Lin, X., Liu, R., Cao, Y., Zou, L., Li, Q., Wu, Y., Liu, Y., Yin, D., & Xu, G. (2025). Contrastive Modality-Disentangled Learning for Multimodal Recommendation. ACM Transactions on Information Systems, 43(3), Article 70. https://doi.org/10.1145/3715876 Guo, S., Wang, C., Gao, C., Luo, W., Han, P., Liao, Q., & Xu, G. (2025). Improving Long-tail Classification via Decoupling and Regularisation. CAAI Transactions on Intelligence Technology, 10(1), 62-71. https://doi.org/10.1049/cit2.12374 Lai, W., Xie, H., Xu, G., & Li, Q. (2025). RVISA: Reasoning and Verification for Implicit Sentiment Analysis. IEEE Transactions on Affective Computing, Early Access, 1-12. https://doi.org/10.1109/TAFFC.2025.3537799 Li, A., Yang, B., Huo, H., Hussain, F. K., & Xu, G. (2025). Self-supervised Dual Graph Learning for Recommendation. Knowledge-Based Systems, 310, Article 112967. https://doi.org/10.1016/j.knosys.2025.112967 Yu, D., Li, Q., Wang, X., & Xu, G (2025). A Causal-based Attribute Selection Strategy for Conversational Recommender Systems. IEEE Transactions on Knowledge and Data Engineering, 37(5), 2169-2182. https://doi.org/10.1109/TKDE.2025.3543112 Cai, Q., Cao, J., Xu, G., & Zhu, N. (2025). Distributed Recommendation Systems: Survey and Research Directions. ACM Transactions on Information Systems, 43(1), Article 10. https://doi.org/10.1145/3694783 Tang, H., Wu, S., Sun, X., Zeng, J., Xu, G., & Li, Q. (2025). TCGC: Temporal Collaboration-Aware Graph Co-Evolution Learning for Dynamic Recommendation. ACM Transactions on Information Systems, 43(1), Article 5. https://doi.org/10.1145/3687470 Sui, S., Han, Q., Lu, D., Wu, S., & Xu, G. (2024). A Novel Complex Network Prediction Method Based on Multi-granularity Contrastive Learning. CCF Transactions on Pervasive Computing and Interaction, 6, 394-405. https://doi.org/10.1007/s42486-024-00174-9 Wu, Z., Liu, Y., Cen, J., Zheng, Z., & Xu, G. (2024). A Cross-domain Knowledge Tracing Model Based on Graph Optimal Transport. World Wide Web, 28, Article 10. https://doi.org/10.1007/s11280-024-01311-1 Yang, H., Wang, Y., Zhao, X., Chen, H., Yin, H., Li, Q., & Xu, G. (2024). Multi-level Graph Knowledge Contrastive Learning. IEEE Transactions on Knowledge and Data Engineering, 36(12), 8829-8841. https://doi.org/10.1109/TKDE.2024.3466530 Hanna, B., Xu, G., Wang, X., & Hossain, J. (2024). Integrating UN Sustainable Development Goals into Family Business Practices: A Perspective Article. Journal of Family Business Management, 14(6), 1203-1211. https://doi.org/10.1108/JFBM-10-2023-0243 Li, Z., Yang, C., Chen, Y., Wang, X., Chen, H., Xu, G., Yao, L., & Sheng, M. (2024). Graph and Sequential Neural Networks in Session-based Recommendation: A Survey. ACM Computing Surveys, 57(2), Article 40. https://doi.org/10.1145/3696413 Duong, T.D., Li, Q., & Xu, G. (2024). Causality-based Counterfactual Explanation for Classification Models. Knowledge-Based Systems, 300, Article 112200. https://doi.org/10.1016/j.knosys.2024.112200 Wang, X., Li, Q., Yu, D., Huang, W., Li, Q., & Xu, G. (2024). Neural Causal Graph Collaborative Filtering. Information Sciences, 677, Article 120872. https://doi.org/10.1016/j.ins.2024.120872 Wang, X., Li, Q., Yu, D., Li, Q., & Xu, G. (2024). Reinforced Path Reasoning for Counterfactual Explainable Recommendation. IEEE Transactions on Knowledge and Data Engineering, 36(7), 3443-3459. https://doi.org/10.1109/TKDE.2024.3354077 Yu, D., Wang, X., Xiong, Y., Shen, X., Wu, R., Wang, D., Zou, Z., & Xu, G. (2024). MHANER: A Multi-source Heterogeneous Graph Attention Network for Explainable Recommendation in Online Games. ACM Transactions on Intelligent Systems and Technology, 15(4), Article 85. https://doi.org/10.1145/3626243 Yicong Li; Xiangguo Sun; Hongxu Chen; Sixiao Zhang; Yu Yang; Guandong Xu (2024). Attention is not the only choice: Counterfactual reasoning for path-based explainable recommendation. IEEE Transactions on Knowledge and Data Engineering, 36(9), 4458-4471. https://doi.org/10.1109/TKDE.2024.3373608 SDGs infomation: 9 - Industry, Innovation and Infrastructure, 10 - Reduced Inequality Xiangmeng Wang, Qian Li, Dianer Yu, Qing Li, Guandong Xu (2024). Counterfactual explanation for fairness in recommendation. ACM Transactions on Information Systems, 42(4), Article 106. https://doi.org/10.1145/3643670 SDGs infomation: 5 - Gender Equality, 9 - Industry, Innovation and Infrastructure Yicong Li, Xiangguo Sun, Hongxu Chen, Sixiao Zhang, Yu Yang, Guandong Xu (2024). Attention is not the only choice: Counterfactual reasoning for path-based explainable recommendation. IEEE Transactions on Knowledge and Data Engineering, 36(9), 4458-4471. https://doi.org/10.1109/TKDE.2024.3373608 Islam, M. R., Akter, S., Islam, L., Razzak, I., Wang, X., & Xu, G. (2024). Strategies for Evaluating Visual Analytics Systems: A Systematic Review and New Perspectives. Information Visualization, 23(1), 84-101. https://doi.org/10.1177/14738716231212568
Conference Papers Wang, D., Dong, J., Deng, J., Long, J., Liu, T., Barelas, G., Taylor, A., Kapnissis, S., Yang, F., Rabinovich, A., & Xu, G. (2026, July). FilterRec: An intent-aware framework for dynamic filter recommendation. [Paper presentation]. The ACM Web Conference 2026, Dubai, United Arab Emirates. https://doi.org/10.1145/3774904.3792892 Feng Zhao, Xianggan Liu, Long Wang, Ruilin Zhao, Yu Yang, Guandong Xu (2026, May). CoT-F: Leveraging Chain-of-Thought Families in Large Language Models for Complex Question Answering. The International Conference on Database Systems for Advanced Applications (DASFAA), South Korea. https://doi.org/10.1007/978-981-92-0369-7_35 Hong Zhang, Feng Zhao, Ruilin Zhao, Yu Yang, Guandong Xu (2026, May). MKLoRA: Multi-Knowledge Collaboration via Intermediate Representation Splitting of LoRA. The Database Systems for Advanced Applications (DASFAA), South Korea. https://doi.org/10.1007/978-981-92-0369-7_25 Feng Zhao, Kangzheng Liu, Teng Peng, Yu Yang, & Guandong Xu (2026, April). DyMRL: Dynamic Multispace Representation Learning for multimodal event forecasting in knowledge graph. Proceedings of the ACM Web Conference 2026, WWW 2026 https://doi.org/10.1145/3774904.3792600 Zhao, R., Zhao, F., & Xu, G. (2026, April). BackChainer: Backward chaining over graph for integrating structured knowledge into large language model reasoning. [Paper presentation] The 31st International Conference on Database Systems for Advanced Applications (DASFAA 2026), Jeju, Korea. https://doi.org/10.1007/978-981-92-0369-7 Zhang, T., Bisht, N., Li, Z., Xu, G., & Wang, X. (2025, November). SarRec: Statistically-guaranteed augmented retrieval for recommendation. [Paper presentation]. The 34th ACM International Conference on Information and Knowledge Management (CIKM '25), Seoul, Korea. https://doi.org/10.1145/3746252.3761054 Bojie Liu, Yu Yang, Guandong Xu (2025, October). GenAI-empowered virtual micro-teaching training system for preservice teachers. Proceedings of behavioural and social computing: 12th International Conference, BESC 2025 https://doi.org/10.1007/978-981-95-7144-4_21 SDGs infomation: 4 - Quality Education Gao, X., Rudd, D.H., Li, Z., Guo, Y., Huo, H., & Xu, G. (2025, October). SpiderGNN: Spatial-aware predictive inference with dynamic edge reasoning for in-building 5G signal estimation. [Paper presentation]. 12th International Conference on Behavioural and Social Computing 2025, Hong Kong. https://doi.org/10.1007/978-981-95-7138-3_9 Kamila Kargabaeva, Yu Yang, Luka Anicin, Milos Stojmenovic, & Guandong Xu (2025, October). Predicting career trajectories after career breaks: A data-driven analysis using LinkedIn profiles. Behavioural and social computing: 12th International Conference, BESC 2025, Hong Kong SAR, China, October 16–18, 2025, Proceedings, Part I https://doi.org/10.1007/978-981-95-7138-3_25 Ma, S., Zeng, Y., Wu, S., & Xu, G. (2025, October). Refining contrastive learning and homography relations for multi-modal recommendation. [Paper presentation]. The 33rd ACM International Conference on Multimedia (MM '25), Dublin, Ireland. https://doi.org/10.1145/3746027.3755779 Shixin Peng, Kun Jiang, Yu Yang, Jingying Chen, & Guandong Xu (2025, October). Framework for diverse depression patients roleplaying and cognitive diagnosis of scales using LLMs based on CoT prompts. Behavioural and social computing: 12th International Conference, BESC 2025, Hong Kong SAR, China, October 16–18, 2025, Proceedings, Part I, Hong Kong. https://doi.org/10.1007/978-981-95-7138-3_26 SDGs infomation: 4 - Quality Education Yakun Chen, Yu Yang, & Guandong Xu (2025, October). AgentLesson: LLM-based multi-agent system for educational lesson plan generation. Behavioural and social computing: 12th International Conference, BESC 2025, Hong Kong SAR, China, October 16–18, 2025, Proceedings, Part I https://doi.org/10.1007/978-981-95-7138-3_11 SDGs infomation: 4 - Quality Education Cao, G., Wu, Z., Huo, H., Ou, Y., & Xu, G. (2025, September). Self-generated cross-modal prompt tuning. [Paper presentation] European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD) 2025, Porto, Portugal. https://doi.org/10.1007/978-3-032-06066-2_22 Qihao Yang, Yu Yang, Sixu An, Tianyong Hao, & Guandong Xu (2025, August). LLM-based collaborative agents with pedagogy-guided interaction modeling for timely instructive feedback generation in task-oriented group discussions. Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence (IJCAI-25) https://doi.org/10.24963/ijcai.2025/1108 SDGs infomation: 4 - Quality Education Bisht, N., Gong, X., & Xu, G. (2025, July). ENSUR: Equitable and statistically unbiased recommendation. [Poster presentation]. 42nd International Conference on Machine Learning, Vancouver, Canada. https://icml.cc/virtual/2025/poster/44363 Huang, S., Gu, Y., Li, Z., Hu, X., Li, Q., & Xu, G. (2025, July). StructFact: Reasoning factual knowledge from structured data with large language models. [Paper presentation]. The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025): Findings of the Association for Computational Linguistics, Vienna, Austria. https://doi.org/10.18653/v1/2025.findings-acl.391 Huang, S., Li, H., Gu, Y., Hu, X., Li, Q., & Xu, G. (2025, July). HyperG: Hypergraph-enhanced LLMs for structured knowledge. [Paper presentation]. SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, Padua, Italy. https://doi.org/10.1145/3726302.3730002 Li, A., Yang, B., Huo, H., Hussain, F., & Xu, G. (2025, July). Hypercomplex knowledge graph-aware recommendation. [Paper presentation]. SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, Padua, Italy. https://doi.org/10.1145/3726302.3730001 Sun, X., Shi, K., Tang, H., Xu, G., & Li, Q. (2025, June). Expert-guided Toxicity Filtration for Debiased Generation. [Paper presentation]. Advances in Knowledge Discovery and Data Mining: The 29th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2025, Sydney, NSW, Australia. https://doi.org/10.1007/978-981-96-8183-9_10 Yunqi Wang, Yu Yang, Longxiang Gao, Xiaoming Wu, & Guandong Xu (2025, April). ReCareer: Hybrid graph neural networks for post-career-break job recommendation. Behavioural and social computing: 12th International Conference, BESC 2025, Hong Kong SAR, China, October 16–18, 2025, Proceedings, Part I https://doi.org/10.1007/978-981-95-7138-3_30 SDGs infomation: 8 - Decent Work and Economic Growth Bisht, N., Gong, X., & Xu, G. (2025, March). CUGF: A Reliable and Fair Recommendation Framework. [Paper presentation]. The 39th Annual AAAI Conference on Artificial Intelligence, Philadelphia, Pennsylvania, USA. https://doi.org/10.1609/aaai.v39i11.33245 Gong, X., Bisht, N., & Xu, G. (2025, March). Conformal Prediction for Partial Label Learning. [Paper presentation]. The 39th Annual AAAI Conference on Artificial Intelligence, Philadelphia, Pennsylvania, USA. https://doi.org/10.1609/aaai.v39i16.33853 Zhang, C., Feng, Z., Zhang, Z., Qiang, J., Xu, G., & Li, Y. (2025, March). Is LLMs Hallucination Usable? LLM-based Negative Reasoning for Fake News Detection. [Paper presentation]. The 39th Annual AAAI Conference on Artificial Intelligence, Philadelphia, Pennsylvania, USA. https://doi.org/10.1609/aaai.v39i1.32089 Shi, K., Sun, X., Wang, D., Fu, Y., Xu, G., & Li, Q. (2025, January). LLaMA-E: Empowering e-Commerce Authoring with Object-interleaved Instruction Following. [Poster presentation]. The 31st International Conference on Computational Linguistics, Abu Dhabi, UAE. https://coling2025.org/ Alsuhaibani, A., Razzak, I., Jameel, S., Wang, X., & Xu, G. (2024, December). CLIMB: Imbalanced Data Modelling Using Contrastive Learning with Limited Labels. [Paper presentation]. Web Information Systems Engineering: 25th International Conference, WISE 2024, Doha, Qatar. https://wise2024-qatar.com/ Liu, K., Zhao, F., Yang, Y., & Xu, G. (2024, October). DySarl: Dynamic Structure-Aware Representation Learning for Multimodal Knowledge Graph Reasoning. [Paper presentation]. The 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, Australia. https://doi.org/10.1145/3664647.3681020 Li, Y., Yang, Y., Cao, J., Liu, S., Tang, H., & Xu, G. (2024, August). Toward Structure Fairness in Dynamic Graph Embedding: A Trend-aware Dual Debiasing Approach. [Paper presentation]. The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2024, Barcelona, Spain. https://doi.org/10.1145/3637528.3671848 Lu, D., Chen, X., Chen, R., Wu, S., & Xu, G. (2024, August). Fairness-aware Mutual Information for Multimodal Recommendation. [Paper presntation]. The 2024 IEEE International Conference on Behavioural and Social Computing (BESC-2024), Harbin, China. https://doi.org/10.1109/BESC64747.2024.10780480 Lu, D., Zhang, H., Li, L., Wu, S., & Xu, G. (2024, August). Cascading Hypergraph Convolution Networks for Multi-behavior Sequential Recommendation. [Paper presentation]. The 2024 IEEE International Conference on Behavioural and Social Computing (BESC-2024), Harbin, China. https://doi.org/10.1109/BESC64747.2024.10780584 Sui, S., Han, Q., Lu, D., Wu, S., & Xu, G. (2024, August). Enhancing Traffic Prediction via Spatial Multi-Granularity Co-Evolving Mechanism. [Paper presntation]. The 2024 IEEE International Conference on Behavioural and Social Computing (BESC-2024), Harbin, China. https://doi.org/10.1109/BESC64747.2024.10780632 Wu, S., & Xu, G. (2024, August). Learning Influential Relationships for Implicit Influence Maximization in Unknown Networks. [Paper presntation]. The 2024 IEEE International Conference on Behavioural and Social Computing (BESC-2024), Harbin, China. https://doi.org/10.1109/BESC64747.2024.10780571 Zhao, R., Zhao, F., Wang, L., Wang, X., & Xu, G. (2024, August). KG-CoT: Chain-of-thought Prompting of Large Language Models over Knowledge Graphs for Knowledge-aware Question Answering. [Paper presentation]. The Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-24), Jeju, South Korea. https://ijcai24.org/index.html Deng, J., Shi, K., Huo, H., Wang, D., & Xu, G. (2024, July). Homogeneous-listing-augmented Self-supervised Multimodal Product Title Refinement. Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2024, Washington D.C., USA. https://doi.org/10.1145/3626772.3661347 Han, Q., Sui, S., Lu, D., Wu, S., Xu, G (2024, July). Enhancing Spatiotemporal Prediction with Intra- and Inter-granularity Contrastive Learning. [Paper presentation]. Database Systems for Advanced Applications: 29th International Conference, DASFAA 2024, Gifu, Japan. https://doi.org/10.1007/978-981-97-5779-4_13 Hu, K., Li, L., Xie, Q., Tao, X., & Xu, G. (2024, July). CrimeAlarm: Towards Intensive iIntent Dynamics in Fine-grained Crime Prediction. [Paper presentation]. Database Systems for Advanced Applications: The 29th International Conference, DASFAA 2024, Gifu, Japan. https://www.dasfaa2024.org/ Huang, S., Li, Q., Wang, X., Yu, D., Xu, G., & Li, Q. (2024, July). Counterfactual Debasing for Multi-behavior Recommendations. [Paper presentation]. Database systems for advanced applications: 29th International Conference, DASFAA 2024, Gifu, Japan. https://www.dasfaa2024.org/ Xiuwen Gong, Nitin Bisht, Guandong Xu (2024, July). Does label smoothing help deep partial label learning?. Proceedings of the 41st International Conference on Machine Learning http://www.scopus.com/inward/record.url?scp=85203788745&partnerID=8YFLogxK Scopus publicationLink to publication in Scopus, https://proceedings.mlr.press/v235/published version SDGs infomation: 4 - Quality Education, 9 - Industry, Innovation and Infrastructure
All Other Outputs Wan, S., Jin, Y., Xu, G., & Nappi, M. (2024). Editorial to Special Issue on Multimedia Cognitive Computing for Intelligent Transportation System. ACM Transactions on Multimedia Computing, Communications, and Applications. https://doi.org/10.1145/3604938

Projects


Develop a Humanoid Robot (EduSphere/Sophia) to Enhance Teaching and Learning in K–12 classrooms (with an initial focus on Primary 5–6 Chinese and Science Education) This cutting-edge three-year project aims to design an AI-powered humanoid robot to enhance teaching and learning in Primary 5–6 Science education. The proposed robot, tentatively named EduSphere (Sophia), will support personalised instruction and bilingual interaction through voice, gesture, touchscreen, and embodied movement. It will assess students' learning status via emotional recognition and facilitate gamified learning. This innovative development project aligns with the university's strategic plan for 2025-2031. The project will deliver a classroom-safe robotic prototype with bilingual, multimodal, and affect-aware interaction, alongside an adaptive learning and analytics framework supporting teacher-guided learning activities, thereby strengthening EdUHK’s position as a leading contributor to AI-driven educational innovation in China and beyond. Project Start Year: 2026, Principal Investigator(s): WANG, Minjuan (XU, Guandong as Co-Investigator) SDGs Information: 3 - Good Health and Well-Being, 4 - Quality Education, 9 - Industry, Innovation and Infrastructure
Special Teaching Assistant with Responsive Sensing (STARS): Research and Development on Multimodal AI-Driven Educational Support Systems for SEN Students The STARS project will develop an innovative multimodal AI system addressing critical support gaps for students with autism and moderate intellectual disabilities. We aim to create a platform providing personalized, real-time learning support by accurately analyzing students' behavioral and emotional states through multiple sensing channels. Our methodology integrates computer vision, audio analysis, and behavioral monitoring with our industrial partner’s (Bridge AI) established wearable and environmental sensor technology. These multimodal inputs will feed novel AI models designed to detect attention, engagement, emotion, and conversational cues in SEN students. We will collect data and validate our approach in Rhenish Church Grace (RCG) School, our partner special school, ensuring the system meets real educational needs. An interactive LLM voice agent will provide adaptive guidance to students, while a comprehensive dashboard will offer teachers data-driven insights and intervention suggestions. STARS will impact special education by: (1) Empowering teachers with objective insights into student states, reducing subjective guesswork; (2) Providing students with a responsive, individualized learning companion; (3) Creating a closed-loop "Sense → Analyze → Respond" system for real-time support. The benefits include reducing teacher burden, increasing student engagement, improving learning outcomes, and addressing the critical "knowledge transfer gap" between classroom settings and real-world applications. Project Start Year: 2025, Principal Investigator(s): FU, Yujun, Eugene (XU, Guandong as Co-Investigator) SDGs Information: 9 - Industry, Innovation and Infrastructure
Using the Attention-Engagement-Error-Feedback-Reflection Pedagogy to Promote Learning-to-Learn Skills among Hong Kong Senior Primary Students / Junior Secondary Students through Understanding Machine Learning Amidst the continuous development of generative artificial intelligence (AI) technologies, machine intelligence might surpass human intelligence in an expanding array of domains. As educators, we must prioritise supporting young learners so that they are well prepared in the AI era. Learning-to-learn is one of the niche areas that we should focus on so that we are able to enable young learners to possess the ability to solve complex problems in specific areas that demand insightful judgement. The purpose is to enable young learners to acquire not only concepts and skills but also insights into solving problems in which machine intelligence is not that capable yet. This project aims to promote learning-to-learn skills through understanding machine learning in K-12 education. The project aims to (1) equip in-service and pre- service teachers ability to facilitate the learning-to-learn process of students using the attention-engagement-error-feedback-reflection (AEER) pedagogy through teaching machine learning concepts and skills; (2) equip Senior Primary Students / Junior Secondary Students in Hong Kong learning-to-learn skills using the AEER pedagogy through understanding machine learning; (3) develop and validate research instruments for evaluating learning-to-learn skills in the K-12 context; (4) seek for international recognition and/or collaboration (e.g., EU countries) with partners after implementation of this initiative. Project Start Year: 2025, Principal Investigator(s): KONG, Siu Cheung, LEE, Chi Kin, John (XU, Guandong as Co-Investigator)
Enhancing Students’ Digital Competency by Developing Interactive and Immersive Educational Games in VRCAVE Project Start Year: 2025, Principal Investigator(s): XU, Guandong, FU, Hong
Revitalizing Mathematical Proficiency using AIScaffoldiaMaths: Empowering Students in Low-Resource Families through AI-Powered Supports in Informal Learning Environments The proposed project aims to empower underprivileged children from low-resource families by leveraging AI and emerging technologies to enhance their mathematics knowledge and skills, foster critical competencies for self-directed learning, and improve affective domains such as confidence and attitudes toward maths in and after-school hours. In collaboration with Durham University, the project will: (1) develop a mathematics learning platform, AIScaffoldiaMaths, incorporating adaptive learning materials facilitated by AI-powered scaffoldings (2) implement this platform across 6 primary schools, reaching 300-500 disadvantaged students from Primary 3 to 6, and extend its use in local welfare and childcare programs. The project will unfold in two consecutive stages: Development & Implementation and Expansion. The system will be designed and developed based on an existing web-based maths system developed by team, with expending the functionality of adaptive learning materials and scaffoldings enabled by Generative AI such as Large Language Models for curriculum generation and optimization, video and audio content generation, and personalised AI avatar tutorial. Usability tests and experimental design will the system will be conducted to evaluate the system performance. Expected benefits include: (1) improved foundational mathematics education outcomes of primary school students; (2) the creation of an AI learning tool for maths education with a variety of resources and support mechanisms that enhance mathematics proficiency, scalable and sustainable over time; (3) a locally-developed AI innovation tailored to the specific needs of students and schools in Hong Kong; (4) a practical solution for bridging educational divides and fostering equity;(5) the establishment of sustainable collaborations with international experts in computer science and AI in education; and (6) enhanced understanding among university students of how design and develop AI tools facilitating personalized learning. Project Start Year: 2025, Principal Investigator(s): SUN, Daner (XU, Guandong as Co-Investigator) SDGs Information: 4 - Quality Education
University Teacher Artificial Intelligence (AI) Competency Model and Professional Learning System for EdUHK and Beyond Project Start Year: 2024, Principal Investigator(s): LIM, Cher Ping (XU, Guandong as Co-Investigator) SDGs Information: 4 - Quality Education, 10 - Reduced Inequality, 17 - Partnerships for the Goals
Child Advancement Technologies & Global Pedagogies Team (ChATGPT) This project aims to establish a global network, the Child Advancement Technologies & Global Pedagogies Team (ChATGPT). The objective is to bring scholars together from around the world who share an interest in advancing early child development and education through technology and pedagogy. The plan involves creating an interactive digital platform fostering collaboration, resource sharing, and knowledge exchange. The platform will form the basis for substantial discussions, collaborations, and global participation. It will also host conferences, webinars, newsletters, and forums to discuss and share findings in early childhood digitalization, neuroscience, AI, and pedagogy. Additionally, an awards program will be instituted to acknowledge exceptional research. With an estimated first-year budget of $962,500 for initial operation costs, the proposal aims to influence global policy-making in early childhood education and applied technologies. Project Start Year: 2024, Principal Investigator(s): LI, Hui (XU, Guandong as Co-Investigator)
Generative Artificial Intelligence Empowered Collaborative Learning: Models, Algorithms, and System This project will research the comprehensive assessment metric of knowledge mastery in collaborative learning. We will devise novel algorithms to predict students’ learning performance in collaborative environment and a novel AIGC-based model to stimulate student learning and maximise the engagement as well as knowledge mastery for every student in the forum. In addition, we will develop an intelligent collaborative learning chatbot with a user-friendly interface to support front-line teaching. Project Start Year: 2024, Principal Investigator(s): XU, Guandong
Uncovering the "Black Box" of Machine Learning: Promoting Artificial Intelligence Literacy with AlphaAI robots in Senior Primary/Junior Secondary Schools across Hong Kong and France Artificial intelligence (AI) including machine learning is changing the landscape of development of the society globally. The promotion of AI literacy to all young learners in their schooling can empower them to have an identification as part of the future AI society (OECD, 2021). Despite the need for nurturing AI literacy, few studies have explored using robots in AI literacy education to “Unboxing the black box of AI” to engage young students in an interactive way (Kong & Yang, 2023). To address these issues, the project aims to (1) equip senior primary/junior secondary students in Hong Kong and France with AI literacy, using the AlphAI robots; (2) develop and implement a neuroscience-informed pedagogical framework, placing a strong emphasis on upskilling in-service teachers to teach AI literacy course in senior primary/junior secondary schools; (3) develop and validate research instruments for AI literacy in K-12 context; and (4) strengthen collaboration and facilitate knowledge exchange between Hong Kong and France in the field of AI literacy education. The findings of the research will make a substantive contribution to the academic field of AI education in both Asian and European regions, establishing a benchmark for future research endeavors and providing valuable insights for the educational policies. Project Start Year: 2024, Principal Investigator(s): KONG, Siu Cheung, LEE, Chi Kin, John (XU, Guandong as Co-Investigator)
AI in Contextual Teaching and Learning (CTL) and Self-directed Learning (SDL) for K-12 Students Project Start Year: 2024, Principal Investigator(s): XU, Guandong
Promoting Internationalisation: Strengthening Support to Non-Local Students and Enhancing EdUHK’s Global Image The project aims to capitalise on the recent relaxation measures announced in the Policy Address, which will double the enrolment ceiling for non-local students in UGC-funded universities. This project proposal outlines a comprehensive plan to enhance the internationalisation image of the University and provide robust support to non-local students. Project Start Year: 2024, Principal Investigator(s): CHENG, May Hung, May (XU, Guandong as Co-Investigator) SDGs Information: 4 - Quality Education, 10 - Reduced Inequality, 17 - Partnerships for the Goals
Towards Demand-driven Education in AI Era: A Predictive Recommender Approach This project will research the impact of AI on job displacement and the evolving demand for job skills, aiming to develop novel algorithms to accurately predict the risk of job displacement and the upcoming trend of demanded job skills. An innovative demand-aware course recommendation system will be developed. Project Start Year: 2024, Principal Investigator(s): XU, Guandong
Developing e-Content for Robotics Education: Using Learning Management System to Promote Blended Learning Model and Content Sharing 開發機器人教育學習教材: 以學習管理平台促進混合式學習及教材分享 This is a large-scale QEF project to develop an online platform to promote STEM education. This project innovates STEM learning by creating a blended learning model through a Learning Management System (LMS). By converting design-driven STEM activities into online courses, it addresses two key barriers in STEM education, i.e., teachers' limited confidence and catering learning diversity. The platform features systematic STEM curriculum structure, innovative 7-Step SWEETIE (Situation, Wondering, Envisioning, Exploration, Thinking-back, Innovation, Extension) teaching pedagogy, six-dimensionally expandable learning kits, flexible learning process, and efficient teacher training. Over 60 schools have adopted the SWEETIE curriculum, training 300+ teachers and benefiting 12,000+ students. Teachers can start to use the platform to teach STEM after just two hours of training. Recently, the SWEETIE platform has developed new online learning resources and systematic assessment methods for the engineering design activities recommended in the new primary science curriculum framework. These enhancements will provide "Teaching + Assessment" one-stop support for the implementation of the new curriculum. Project Start Year: 2023, Principal Investigator(s): WAN, Zhihong (XU, Guandong as Co-Investigator)

Patents


An Intelligent Tutoring System Powered By Llm-Based Collaborative Agents And Its Optimization Method The present invention provides an intelligent tutoring system powered by LLM-based collaborative agents. - A/H05
一种由基于LLM 协作式智能体驱动的智能辅导系统以及其优化方法 The present invention provides an intelligent tutoring system powered by LLM-based collaborative agents. - A/H05