ZHANG-Xiao

张骁的个人主页

This project is maintained by pinkfloyd1989

张骁

中国人民大学,高瓴人工智能学院,准聘助理教授

电子邮箱:zhangx89@ruc.edu.cn

English Homepage

研究兴趣

个人简介

已在本领域相关的国内外学术期刊和会议上发表论文四十余篇,涵盖 ICML、NeurIPS、KDD、SIGIR、AAAI、IJCAI、WWW、ICDE 等人工智能重要国际会议,及 TOIS、《计算机学报》、《中国科学: 信息科学》等计算机学会 A 类期刊,并获得 CCDM 2016、ICPR 2018 优秀论文奖、WWW 2023 最佳论文提名奖、SIGIR-AP 2023 最佳论文奖。研究成果被来自斯坦福大学、法国国家信息与自动化研究所等科研机构的领域专家(A. Rudi、Lei Xing等)引用,所提出的在线核学习算法被国际模式识别学会《IAPR Newsletter》评价为 “promising for large-scale matrix computation and online learning”(参考译文:大规模矩阵计算及在线学习领域的一种有前景的方法)。受邀担任 ICML、KDD、SIGIR、NeurIPS、AAAI、IJCAI、WWW 等多个国际会议的程序委员会委员及资深程序委员会委员。主持科研基金项目包括:国家自然科学基金(面上项目、青年基金项目)、科技部人工智能重大专项子课题、中国科协高端科技创新智库青年项目、中国博士后科学基金特别资助、以及腾讯微信犀牛鸟专项研究计划和快手合作项目等横向项目。

工作经历

教育背景

教授课程

预印本论文

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.

Sunhao Dai, Yuqi Zhou, Liang Pang, Weihao Liu, Xiaolin Hu, Yong Liu, Xiao Zhang, Jun Xu. LLMs may dominate information access: Neural retrievers are biased towards LLM-generated texts, https://arxiv.org/abs/2310.20501.

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.

Changshuo Zhang, Sirui Chen, Xiao Zhang, Sunhao Dai, Weijie Yu, Jun Xu. UOEP: User-oriented exploration policy for enhancing long-term user experiences in recommender systems, https://arxiv.org/abs/2401.09034.pdf.

代表英文论文

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), accepted.

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), accepted.

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), accepted.

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), accepted.

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), accepted.

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), accepted.

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), accepted.

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), accepted.

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), accepted.

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), accepted.

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), accepted.

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), accepted.

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), accepted.

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, accepted.

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, accepted.

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, accepted. (最佳论文奖)

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, accepted. (Spotlight-最佳论文提名奖)

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, accepted.

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), accepted.

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), accepted.

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.

代表中文论文

张骁, 廖士中. 基于局部后悔的在线核选择. 计算机学报, 42(1): 61–72, 2019.

张骁, 胡清华, 廖士中. 基于多源共享因子的多张量填充. 中国科学 : 信息科学, 46(7): 819–833, 2016. (CCDM 最佳学生论文)

廖芸, 张骁, 廖士中. 统一框架下在线核选择的竞争性分析. 计算机科学与探索, 2019, DOI:10.3778/j.issn.1673-9418.1905092.

主要主持项目

受限反馈下的可信在线学习, 国家自然科学基金——面上项目 (No.62376275), 2024.01-2027.12, 主持

在线模型选择的增量素描方法, 国家自然科学基金——青年科学基金项目 (No.62006234), 2021.01-2022.12, 主持

智能社会治理算法设计的风险及应对, 中国科协高端科技创新智库青年项目, 2020.08-2021.06, 主持

中国博士后科学基金第 14 批特别资助(站中), 2021.07-2022.09, 主持

面向多场景、多任务、转化延迟场景的推荐算法研究, 腾讯微信犀牛鸟专项研究计划, 2020.05-2021.05, 主持

基于因果推断的推荐系统归因与可控推荐模型研究,腾讯微信犀牛鸟专项研究计划, 2023.07-2024.07, 主持

基于用户搜索和浏览行为的推荐系统研究, 快手合作项目, 2021.05-2023.06, 主持

主要参与项目

商品搜索中的个性化内容混排模型研究,阿里 Air 合作项目,2021.03–2022.03, 参与

大规模核方法模型选择的随机方法,国家自然科学基金面上项目, 2017.01–2020.01, 参与

主要获奖