Victor Junqiu Wei

	Research Assistant Professor Department of Computer Science and Engineering (CSE) Hong Kong University of Science and Technology (HKUST) Clear Water Bay, Kowloon Hong Kong, China Office: Room 2538 Tel: +852-2766 7238 Email: wjqjsnj@gmail.com

General Information

Biography Victor Junqiu WEI is currently working as a research assistant professor in the Department of Computer Science and Engineering (CSE), the Hong Kong University of Science and Technology (HKUST). He obtained his bachelor degree from Nanjing University and PhD degree from Department of Computer Science and Engineering, the Hong Kong University of Science and Technology, under supervision of Prof. Raymond Chi-Wing Wong. From March 2018 to May 2018, he was a visiting student of Prof. Hanan Samet and Prof. David Mount at University of Maryland in US. He had collaborations with Prof. Raymond Chi-Wing Wong, Prof. Pan Hui, Prof. Cheng Long, Prof. Bo Tang, Prof. Irwin King, Prof. Hanan Samet and Prof. David Mount. He also has several years' working experience in the world-famous research labs in the AI industry including Baidu natural language processing (NLP) group, AI group of WeBank and Noah's Ark Lab of Huawei. Research Statement His research interests span spatial-temporal data management (Published in SIGMOD 2017, TKDE 2019, SIGMOD 2020, ICDE 2020, SIGMOD 2023, TODS 2022), graph data management (SIGMOD 2020, TKDD 2022), random sampling (ICDM 2019, ICDE 2020), deep neural networks (AAAI 2021, ACL 2022, EMNLP 2022, ICSE 2023). His vision is to optimize the data management and data mining applications with advanced data structures, machine learning and deep learning algorithms. He served as a program committee member of many top conferences such as ICDE, KDD, PAKDD, SSTD, COLING, NAACL, EMNLP and ACL, etc.

Publications

* denotes the corresponding author. Bo Huang, Victor Junqiu Wei*, Raymond Chi-Wing Wong, Bo Tang*. EAR-Oracle: On Efficient Indexing for Distance Queries between Arbitrary Points on Terrain Surface. To appear in Proceedings of ACM Conference on Management of Data, Seatle, USA, (SIGMOD), 2023. code ** Note: Part of work was done when Bo Huang worked as a research assistant in the Hong Kong Polytechnic University (supported by PolyU internal fund (1-BD47) under the research project (P0039657) of the Hong Kong Polytechnic University) under the supervision of Victor Junqiu Wei. Weibin Wu, Jianping Zhang, Victor Junqiu Wei, Xixian Chen, Zibin Zheng, Irwin King, Michael Lyu. Practical and Efficient Model Extraction of Sentiment Analysis APIs. To Appear in Proceedings of the 45th IEEE/ACM International Conference on Software Engineering (ICSE), 2023. Victor Junqiu Wei, Raymond Chi-Wing Wong, Cheng Long, David M. Mount, Hanan Samet. Proximity Queries on Terrain Surface. Proceedings of ACM Transactions on Database System (TODS), 2022. Dandan Lin, Victor Junqiu Wei* and Raymond Chi-Wing Wong. Effective and Scalable Manifold Ranking-based Image Retrieval with Output Bound. Proceedings of ACM Transactions on Knowledge Discovery from Data, 2022 (TKDD), 2022. Sunzhu Li, Peng Zhang, Guobing Gan, Xiuqing Lv, Benyou Wang, Junqiu Wei and Xin Jiang. Hypoformer: Hybrid Decomposition Transformer for Edge-friendly Neural Machine Translation. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, (EMNLP), 2022. Ningning Wang, Guobing Gan, Peng Zhang, Shuai Zhang, Junqiu Wei, Qun Liu, Xin Jiang. ClusterFormer: Neural Clustering Attention for Efficient and Effective Transformer. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, (ACL), 2022 code Jing Zhang, Peng Zhang, Baiwen Kong, Junqiu Wei, Xin Jiang. Continuous Self-Attention Models with Neural ODE Networks. Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, (AAAI), 2021 Victor Junqiu Wei, Raymond Chi-Wing Wong, Cheng Long. Architecture-Intact Oracle for Fastest Path and Time Queries on Dynamic Spatial Networks. Proceedings of ACM Conference on Management of Data (SIGMOD), Portland, USA, (SIGMOD), 2020 (Nominee of the Best Paper Award) slides video Victor Junqiu Wei, Raymond Chi-Wing Wong, Cheng Long, Pan Hui. On Nearby-Fit Spatial Keyword Queries (Extended Abstract). Proceedings of the 36th IEEE International Conference on Data Engineering, (ICDE), 2020 slides video code Dandan Lin, Raymond Chi-Wing Wong, Min Xie, Victor Junqiu Wei. Index-Free Approach with Theoretical Guarantee for Efficient Random Walk with Restart Query. Proceedings of the 36th IEEE International Conference on Data Engineering, (ICDE), 2020 code Victor Junqiu Wei, Raymond Chi-Wing Wong, Cheng Long, Pan Hui. On Nearby-Fit Spatial Keyword Queries. Proceedings of the IEEE Transaction on Knowledge and Data Engineering, (TKDE), 2019 slides video code Dandan Lin, Victor Junqiu Wei and Raymond Chi-Wing Wong. First Index-Free Manifold Ranking-based Image Retrieval with Output Bound. Proceedings of the IEEE International Conference on Data Mining, Beijing, China, (ICDM), 2019 code Cheng Long, Raymond Chi-Wing Wong and Victor Junqiu Wei. Profit Maximization with Sufficient Customer Satisfactions. Proceedings of ACM Transactions on Knowledge Discovery from Data (TKDD), 2018 Victor Junqiu Wei, Raymond Chi-Wing Wong, Cheng Long, David M. Mount. Distance Oracle on Terrain Surface. Proceedings of ACM Conference on Management of Data, Chicago, USA (SIGMOD), 2017 slides video code

Preprints

Junqiu Wei, Qun Liu, Yinpeng Guo, Xin Jiang. Training Multilingual Pre-trained Language Model with Byte-level Subwords. Technical Report, arXiv preprint arXiv:2101.09469. project webpage Junqiu Wei, Xiaozhe Ren, Xiaoguang Li, Wenyong Huang, Yi Liao, Yasheng Wang, Jiashu Lin, Xin Jiang, Xiao Chen, Qun Liu. NEZHA: Neural Contextualized Representation for Chinese Language Understanding. Technical Report, arXiv preprint arXiv:1909.00204, 2019. project webpage media Shuai Zhang, Peng Zhang, Xindian Ma, Junqiu Wei, Qun Liu. TensorCoder: Dimension-Wise Attention via Tensor Representation for Natural Language Modeling. Technical Report, arXiv preprint arXiv:2008.01547

Teaching

Past Courses Database Systems (COMP 2411, Fall 2022, Hong Kong Polytechnic Univeristy) Wireless Networks and Mobile Computing (COMP 5327, Spring 2022, Hong Kong Polytechnic University) Knowledge and Data Management (COMP 4135, Spring 2022, Hong Kong Polytechnic University)

Awards and Honors

Potentially High Value Patent Award, Huawei Technologies, Aug. 2021 Nominee of the Best Paper Award of SIGMOD 2020, Apr. 2020 Future Star of Huawei Technologies., Nov. 2020 Star of Huawei 2012 Lab (i.e., Huawei Research Department), Apr. and Dec. 2020, Apr. 2021 (Three times) Gold Team Medal of Huawei Technologies., Jan. 2020 OKR Star of Huawei Noah’s Ark Lab (Top 1% per season), Nov. 2019 Overseas Research Awards of HKUST, Nov. 2017 Research Travel Grant of HKUST, Jun. 2017 Student Travel Award of SIGMOD, Apr. 2017 Postgraduate Studentship of HKUST, 2013 - 2018 Outstanding Undergraduate Thesis of Nanjing University, Jun. 2013 Renmin Schoolarship, 1st Prize, Oct. 2010 Excellent Undergraduate Student of Nanjing University, Oct. 2010 2nd Prize Provincial, Chinese Physics Olympiad, Oct. 2008

Professional Services

PC Member KDD (2023), ACL (2021, 2022, 2023), ICDE (2021, 2022), NAACL (2021, 2022), EMNLP (2021, 2022), CIKM (2021, 2022), COLING (2018, 2020), PAKDD (2020, 2021, 2022, 2023), SIGSPATIAL (2023), SSTD (2021), BigData (2019, 2020), BigComp (2019, 2020) Journal Reviewer Pattern Recognition Letter (2021), IEEE Transaction on Knowledge and Data Engineering (2022), Journal of Knowledge-based System (2022), Journal of Aitificial Intelligence (2021), ACM Computing Surveys (2023) Best Demo Committee Member ICDE (2022) External Reviewer VLDB (2015), CIKM (2015, 2016, 2017), PAKDD (2016, 2017), IJCAI (2016), KDD (2016, 2017), ICDE (2016), ICDM (2017), SIGMOD (2018, 2020), WWW (2019)

Student Supervision

It is my great pleasure of working with these intelligent and hard-working students. Yuqi Zha (Apr. 2022 - Dec. 2022, Part-Time Research Assistant, Research Topic: Trajectory Simplification)     Bachelor degree from Sichuan University, Master Degree from the Hong Kong Polytechnic University     Now: Phd Student in City Univeristy of Hong Kong Yan Ge (Aug. 2022 - Present, Full-Time Research Assistant, Research Topic: Natural Language to Visualization)     Master degree from Jilin University     Achievement under My Supervision: One Paper Submitted to ACL 2023 Bo Huang (Aug. 2022 - Present, Full-Time Research Assistant, Research Topic: Shortest Distance Queries on Terrain Surfaces)     Bachelor and Master degree both from the Southern University of Science and Technology     Achievement under My Supervision: One Paper Published in SIGMOD 2023

Invited Talks

"Distance Oracle on Terrain Surface", SIGMOD, May 2017 [Video] "Random Walk-based Sampling on Graphs", Baidu Natural Language Processing Group, Jan. 2018 [PPT] "Experience Sharing on Job Hunting", Phd Forum, MDM 2019 [PPT] "华为预训练语言模型技术与行业应用 (Pre-trained Language Model Technologies and Applications in Huawei)", AICon 2019 [Media] "On Nearby-Fit Spatial Keyword Queries", ICDE, April 2020 [Video] "Architecture-Intact Oracle for Fastest Path and Time Queries on Dynamic Spatial Networks", SIGMOD, June 2020 [Video] "Word Representation Learning on Natural Language Processing", AI in "X" Workshop, IEEE Computer Intelligence Hong Kong Chapter, Dec 2020 [PPT] "On Boosting Spatial Data Management with Efficient Indexing Structures", Departmental Seminar of Computer Science and Engineering, Hong Kong University of Science and Technology, Jan. 2022 [LINK] "Key Techniques in Pre-trained Language Models", Shenzhen Institute of Computing Sciences, Aug. 2022