Xiao Zhang

Tenure-Track Associate Professor, Gaoling School of Artificial Intelligence, Renmin University of China

e-mail：zhangx89@ruc.edu.cn

PERSONAL PROFILE

Xiao Zhang is a tenure-track Associate Professor and Ph.D. advisor at the Gaoling School of Artificial Intelligence, Renmin University of China, and a recipient of the Distinguished Young Scholar award. He has published over 40 papers in leading international conferences and journals, including ICML, NeurIPS, KDD, SIGIR, AAAI, IJCAI, WWW, ICDE, and VLDB, as well as top-tier journals such as IEEE TKDE, ACM TOIS, Journal of Computer Science, and Science China: Information Sciences. His work has been recognized with several prestigious awards, including the SIGIR 2024 Best Short Paper Nomination, VLDB 2024 Best Paper Nomination, WWW 2023 Best Paper Nomination, SIGIR-AP 2023 Best Paper Award, ICPR 2018 Best Paper Award, CCFAI 2017 Best Paper Nomination, and CCDM 2016 Best Paper Award. He has been invited to serve on the program committees and senior program committees of several top conferences, including ICML, KDD, SIGIR, NeurIPS, AAAI, IJCAI, and WWW.

RESEARCH INTERESTS

Key Words: Online&Reinforcement Learning; Causal&Turstworthy Machine Learning; Large Language Models; Information Retrieval.
Research Summary: Dr. Xiao Zhang’s group focuses on developing accountable, controllable and efficient machine learning theory and learning algorithm in sequential prediction/decision scenarios, especially the new paradigm of causal machine learning and large models. They aim to develop useful and robust machine learning algorithms in information retrieval applications.
Research Directions:
- Online Learning & Reinforcement Learning: Theoretical analysis and algorithm design for online learning & reinforcement learning, as well as low-resource consumption learning algorithms for streaming data.
- Causal Learning & Trustworthy Learning: Focused on integrating causal inference methods into machine learning, with an emphasis on developing theories, methods, algorithms, and applications that ensure controllability and fairness in machine learning.
- Information Retrieval Applications: Applications in recommender systems, search, ranking, with a particular focus on large models empowering information retrieval.

WORK EXPERIENCE

2024-present, Renmin University of China, Associate Professor.
2022-2024, Renmin University of China, Assistant Professor.
2020-2022, Renmin University of China, Postdoctoral Researcher. Supervisor: Prof. Ji-Rong Wen.

EDUCATION

2015-2019，Tianjin University, Ph.D., Computer Application Technology, Advisor: Prof. Shizhong Liao.
2012-2015, Northwestern Polytechnical University, M.S., Computing Mathematics, Advisor: Prof. Quan Lu.
2008-2012，Shanxi University, B.Sc., Information and Computing Sciences.

TEACHING

Reinforcement Learning (Undergraduate course, 2024)
Advanced Reinforcement Learning (Graduate course, Fall 2024)
Intelligent Information Retrieval (Graduate course, Fall 2024, co-teaching with Professor Xu Jun)
AI Ethics and Safety (Undergraduate course, Spring 2024)
Introduction to Artificial Intelligence (Undergraduate course, Spring 2024)
Advanced Reinforcement Learning (Graduate course, Fall 2023)
Advanced Reinforcement Learning (Graduate course, Fall 2022)
Massive Data Mining (Graduate course, Fall 2021, co-teaching with Professor Liu Yong)

PREPRINT PAPERS

Chenglei Shen, Jiahao Zhao, Xiao Zhang, Weijie Yu, Ming He, Jianping Fan. Generating model parameters for controlling: Parameter diffusion for controllable multi-task recommendation, https://arxiv.org/abs/2410.10639.pdf.

Chenglei Shen, Xiao Zhang, Teng Shi, Changshuo Zhang, Guofu Xie, Jun Xu. A survey of controllable learning: Methods and applications in information retrieval, https://arxiv.org/abs/2407.06083.pdf. [ A newly released survey on Controllable Learning is out now, stay tuned!]

Dongxie Wen, Hanyan Yin, Xiao Zhang, Zhewei Wei. Matrix sketching in bandits: Current pitfalls and new framework, https://arxiv.org/abs/2410.10258.pdf.

Dongxie Wen, Xiao Zhang, Zhewei Wei. Fast second-order online kernel learning through incremental matrix sketching and decomposition, https://arxiv.org/abs/2410.11188.pdf.

Yi Xu, Weiran Shen, Xiao Zhang, Jun Xu. IBCB: Efficient inverse batched contextual bandit for behavioral evolution history, https://arxiv.org/abs/2403.16075.pdf.

Chenglei Shen, Guofu Xie, Xiao Zhang, Jun Xu. On the decision-making abilities in role-playing using large language models, https://doi.org/10.48550/arXiv.2210.06719.

REPRESENTATIVE PAPERS

Xiao Zhang, Teng Shi, Jun Xu, Zhenhua Dong, Ji-Rong-Wen. Model-agnostic causal embedding learning for counterfactually group-fair recommendation. IEEE Transactions on Knowledge and Data Engineering (TKDE), doi: 10.1109/TKDE.2024.3424906.

Yuan Wang, Zhiyu Li, Changshuo Zhang, Sirui Chen, Xiao Zhang*, Jun Xu, Quan Lin. Do not wait: Learning re-ranking model without user feedback at serving time in e-commerce. Proceedings of the 18th ACM Conference on Recommender Systems (RecSys 2024), short paper.

Kepu Zhang, Teng Shi, Sunhao Dai, Xiao Zhang*, Yinfeng Li, Jing Lu, Xiaoxue Zang, Yang Song, Jun Xu. SAQRec: Aligning recommender systems to user satisfaction via questionnaire feedback. Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (CIKM 2024).

Zhongxiang Sun, Zihua Si, Xiaoxue Zang, Kai Zheng, Yang Song, Xiao Zhang, Jun Xu. Large language models enhanced collaborative filtering. Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (CIKM 2024).

Sunhao Dai, Yuqi Zhou, Liang Pang, Weihao Liu, Xiaolin Hu, Yong Liu, Xiao Zhang, Gang Wang, Jun Xu. Neural retrievers are biased towards LLM-generated content. Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2024).

Hanyan Yin, Dongxie Wen, Jiajun Li, Zhewei Wei, Xiao Zhang, Zengfeng Huang, Feifei Li. Optimal matrix sketching over sliding windows. Proceedings of the 50th International Conference on Very Large Databases (VLDB 2024). (Best Research Paper Nominations)

ZhongXiang Sun, Kepu Zhang, Haoyu Wang, Xiao Zhang, Jun Xu. Effective in-context example selection through data compression. ACL Findings (2024).

Changshuo Zhang, Sirui Chen, Xiao Zhang*, Sunhao Dai, Weijie Yu and Jun Xu. Reinforcing long-term performance in recommender systems with user-oriented exploration policy. Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2024).

Zhongxiang Sun, Zihua Si, Xiao Zhang, Xiaoxue Zang, Yang Song, Hongteng Xu and Jun Xu. To search or to recommend: Predicting open-app motivation with neural Hawkes process. Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2024).

Teng Shi, Zihua Si, Jun Xu, Xiao Zhang, Xiaoxue Zang, Kai Zheng, Dewei Leng, Yanan Niu and Yang Song. UniSAR: Modeling user transition behaviors between search and recommendation. Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2024).

Sunhao Dai, Changle Qu, Sirui Chen, Xiao Zhang and Jun Xu. ReCODE: Modeling repeat consumption with neural ODE. Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2024), short paper. (Best Short Paper Nominee)

Zihua Si, Zhongxiang Sun, Jiale Chen, Guozhang Chen, Xiaoxue Zang, Kai Zheng, Yang Song, Xiao Zhang, Jun Xu and Kun Gai. Generative retrieval with semantic tree-structured identifiers and contrastive learning. Proceedings of the 2nd International ACM SIGIR Conference on Information Retrieval in the Asia Pacific (SIGIR-AP 2024).

Peiyu Liu, Ze-Feng Gao, Xiao Zhang, Wayne Xin Zhao, Ji-Rong Wen. Enhancing parameter-efficient fine-tuning with simple calibration based on stable rank. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024).

Chen Xu, Jun Xu, Yiming Ding, Xiao Zhang, Qi Qi. FairSync: Ensuring amortized group exposure in distributed recommendation retrieval. Proceedings of the 2024 ACM Web Conference (WWW 2024).

Jianwen Yang, Xiao Zhang*, Jun Xu. Smooth start: a unified approach for gradual transition from cold to old in recommender systems. Proceedings of the 49th IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP 2024).

Sunhao Dai, Ninglu Shao, Jieming Zhu, Xiao Zhang, Zhenhua Dong, Jun Xu, Quanyu Dai, Ji-Rong Wen. Modeling user attention in music recommendation. Proceedings of the 40th IEEE International Conference on Data Engineering (ICDE 2024).

Xiao Zhang, Ninglu Shao, Zihua Si, Jun Xu, Wenhan Wang, Hanjing Su, Ji-Rong Wen. Reward imputation with sketching for contextual batched bandits. Advances in Neural Information Processing Systems 35 (NeurIPS 2023), 64577-64588, 2023.

Chuhao Jin, Yutao Zhu, Lingzhen Kong, Shijie Li, Xiao Zhang, Ruihua Song, Xu Chen, Yuchong Sun, Yu Chen, Jun Xu. Joint semantic and strategy matching for persuasive dialogue. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP).

Chenglei Shen, Xiao Zhang*, Wei Wei, Jun Xu. HyperBandit: Contextual bandit with hypernewtork for time-varying user preferences in streaming recommendation. Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (CIKM 2023), 2239–2248, 2023.

Zhongxiang Sun, Zihua Si, Xiaoxue Zang, Dewei Leng, Yanan Niu, Yang Song, Xiao Zhang, Jun Xu. KuaiSAR: A unified search and recommendation dataset, Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (CIKM 2023 Resource Paper).

Sirui Chen, Yuan Wang, Zijing Wen, Zhiyu Li, Changshuo Zhang, Xiao Zhang*, Quan Lin, Cheng Zhu, Jun Xu. Controllable multi-objective re-ranking with policy hypernetworks. Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023).

Zhongxiang Sun, Jun Xu, Xiao Zhang, Zhenhua Dong and Ji-Rong Wen. Law article-enhanced legal case matching: A causal learning approach. Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2023).

Zihua Si, Zhongxiang Sun, Xiao Zhang*, Jun Xu, Xiaoxue Zang, Yang Song, Kun Gai and Ji-Rong Wen. When search meets recommendation: Learning disentangled search representation for recommendation. Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2023), 1313-1323, 2023.

Sunhao Dai, Ninglu Shao, Haiyuan Zhao, Weijie Yu, Zihua Si, Chen Xu, Zhongxiang Sun, Xiao Zhang and Jun Xu. Uncovering ChatGPT’s capabilities in recommender systems. RecSys 2023 Late Breaking Results (LBR) track, 2023.

Sirui Chen, Xiao Zhang, Xu Chen, Zhiyu Li, Yuan Wang, Quan Lin and Jun Xu. Reinforcement re-ranking with 2D grid-based recommendation panels. Proceedings of the 1st International ACM SIGIR Conference on Information Retrieval in the Asia Pacific, 2023.

Haiyuan Zhao, Jun Xu, Xiao Zhang, Guohao Cai, Zhenhua Dong and Ji-Rong Wen. Unbiased top-$k$ learning to rank with causal likelihood decomposition. Proceedings of the 1st International ACM SIGIR Conference on Information Retrieval in the Asia Pacific, 2023. (Best Paper Reward)

Chen Xu, Sirui Chen, Jun Xu, Weiran Shen, Xiao Zhang, Gang Wang, Zhenhua Dong. P-MMF: Provider max-min fairness re-ranking in recommender system. Proceedings of the Web Conference 2023 (WWW 2023), 2023. (Spotlight-Best Research Paper Nominations)

Zihua Si, Zhongxiang Sun, Xiao Zhang, Jun Xu, Yang Song, Xiaoxue Zang, Ji-Rong Wen. Enhancing recommendation with search data in a causal learning manner. ACM Transactions on Information Systems (TOIS), 2023.

Haiyuan Zhao, Jun Xu, Xiao Zhang, Guohao Cai, Zhenhua Dong, Ji-Rong Wen. Separating examination and trust bias from click predictions for unbiased relevance ranking. Proceedings of the 16th ACM International Conference on Web Search and Data Mining (WSDM 2023).

Haonan Jia, Xiao Zhang, Jun Xu, Wei Zeng, Hao Jiang, Xiaohui Yan. Variance reduction for deep Q-Learning using stochastic recursive gradient, Proceedings of the 29th International Conference on Neural Information Processing (ICONIP 2022).

Xiao Zhang, Sunhao Dai, Jun Xu, Zhenhua Dong, Quanyu Dai, Ji-Rong Wen. Counteracting user attention bias in music streaming recommendation via reward modification. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2022), 2504–2514, 2022.

Zihua Si, Xueran Han, Xiao Zhang, Jun Xu, Yue Yin, Yang Song, Ji-Rong Wen. A model-agnostic causal learning framework for recommendation using search data. Proceedings of the Web Conference 2022 (WWW 2022), 224–233, 2022.

Xiao Zhang, Haonan Jia, Hanjing Su, Wenhan Wang, Jun Xu, Ji-Rong Wen. Counterfactual reward modification for streaming recommendation with delayed feedback. Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021), 41-50, 2021.

Xiao Zhang, Shizhong Liao, Jun Xu, Ji-Rong Wen. Regret bounds for online kernel selection in continuous kernel space. Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI 2021), 10931-10938, 2021.

Xiao Zhang, Shizhong Liao. Hypothesis sketching for online kernel selection in continuous kernel space. Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI 2020), 2498–2504, 2020.

Xiao Zhang, Shizhong Liao. Incremental randomized sketching for online kernel learning. Proceedings of the 36th International Conference on Machine Learning (ICML 2019), 7394–7403, 2019.

Shizhong Liao, Xiao Zhang*. Online kernel selection via tensor sketching. Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM 2019), 801–810, 2019.

Xiao Zhang, Shizhong Liao. Online kernel selection via incremental sketched kernel alignment. Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI 2018), 3118–3124, 2018.

Xiao Zhang, Shizhong Liao. Tensor completion via multi-shared-modes canonical correlation analysis. Neurocomputing, 205: 106–115, 2016.

Xiao Zhang, Yun Liao, Shizhong Liao. A survey on online kernel selection for online kernel learning. WIREs Data Mining and Knowledge Discovery, 9(2): e1295, 2019.

Shan Xu, Xiao Zhang, Shizhong Liao. New online kernel ridge regression via incremental predictive sampling. Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM 2019), 791–800, 2019.

Shan Xu, Xiao Zhang, Shizhong Liao. A linear incremental Nystrom method for online kernel learning. Proceedings of the 24th International Conference on Pattern Recognition (ICPR 2018), 2256–2261, 2018. (Best Student Paper)

*: Corresponding author.

Major Awards

August 2024: VLDB 2024 Best Paper Nominee
July 2024: SIGIR 2024 Best Short Paper Nominee
November 2023: SIGIR-AP 2023 Best Paper Award
April 2023: WWW 2023 Best Paper Nominee
November 2018: Best Paper Award at ICPR 2018
August 2017: Best Paper Nominee at CCFAI 2017
May 2016: Best Paper Award at CCDM 2016
November 2011: First Prize in the National College Student Mathematical Contest in Modeling
November 2010: First Prize in the National College Student Mathematical Contest in Modeling