😬 Biography

I am a Ph.D. candidate at School of Artificial Intelligence (opens new window) in Nanjing University (opens new window), and a member of LAMDA Group (opens new window), which is led by Prof. Zhi-Hua Zhou (opens new window).

I received my B.Sc. degree from Software College (opens new window) at Jilin University (opens new window) in 2019. In September 2019, I was admitted to study for a M.Sc. degree in Nanjing University without entrance examination, and I completed my M.Sc. degree in 2022. From July 2022 to August 2023, I worked as a algorithm engineer at Shopee (opens new window). And then, in 2023, I've returned to LAMDA to pursue a full-time Ph.D. degree.

📖 Research Interests

I am interested in machine learning and data mining, especially the followiong:

  • Transfer Learning
  • Semi-supervised Learning
  • Ranking Model in Search Engine & Recommendation System (2 years of work experience on Search&Recommendation)

📑 Publications

Journal Papers

  • Enhancing Unsupervised Domain Adaptation by Exploiting the Conceptual Consistency of Multiple Self-supervised Tasks
    • Hui Sun, and Ming Li.
    • SCIENCE CHINA Information Sciences (SCIS), 2023, 66: 142101 (CCF-A Journal, SCI)

Conference Papers

  • Cooperative and Adversarial Learning: Co-Enhancing Discriminability and Transferability in Domain Adaptation
    • Hui Sun, Zheng Xie, Xin-Ye Li, and Ming Li.
    • The 37th AAAI Conference on Artificial Intelligence (AAAI), 2023. (CCF-A Conference)
  • Semi-Supervised Learning with Support Isolation by Small-Paced Self-Training
    • Zheng Xie, Hui Sun, and Ming Li.
    • The 37th AAAI Conference on Artificial Intelligence (AAAI), 2023. (CCF-A Conference)
  • Clustered Embedding Learning for Recommender Systems
    • Yizhou Chen, Guangda Huzhang, Anxiang Zeng, Qingtao Yu, Hui Sun, Heng-Yi Li, Jingyi Li, Yabo Ni, Han Yu, and Zhiming Zhou.
    • The World Wide Web Conference (WWW), 2023. (CCF-A Conference)

Patents

  • 一种面向环境变化的无监督迁移学习图像分类算法
    • 黎铭,孙辉,周志华
    • 202210461879.4,专利公布中,2022

🎖 Awards & Honors

● Value Star Awards (8/200+)
Shopee, 2022.12
● Artificial Intelligence Scholarship
Nanjing University, 2019.10
● China Collegiate Computing Contest (CCCC), Outstanding Winner of Jilin Province
Jilin, 2018.03
● The ACM-ICPC Asia Regional Contest, Silver Medal
Nanning, 2017.12
● The ACM-ICPC Asia Regional Contest East Continent League Final (EC-Final), Bronze Medal
Shanghai, 2017.12
● The Jilin Province Collegiate Programming Contest, Gold Medal
Changchun, 2017.05
● The Northeast Collegiate Programming Contest, Gold Medal
Changchun, 2016.09

🧱 Work Experience

● Search Algorithm Engineering at Shopee, Search
Jul.2022-Aug.2023

Primarily responsible for maintaining and optimizing the foundational E-commerce search ranking model, initially used in fine-ranking and extended to recall, coarse-ranking, and long-tail scenarios.

  • Model Infrastructure Maintenance (Framework and Speed Optimization):

    • Deconstrucing neural networks into configurable blocks, enabling maximum loading of pre-trained parameters when modifying features/network blocks. Data needed for model convergence after modification: Reduced from 2+ months to 1 week.
    • Shared user-side computations in each request. Offline training speed: increased from 37 to 76(+105%) samples / (cpu * sec.); Online inference runtime: Reduced from 95.5ms to 28.8ms (speed +232%).
  • Algorithm:

    • Clustered Embedding Learning (CEL): Improved CTR AUC by +0.6%, reduced model size. Our research paper has been accepted at WWW23. My primary role was its implementation in our real-world ranking model, achieving a 10x speed increase.
    • Multi-task: Implemented Progressive Layered Extraction (PLE), resulting in a CTR AUC+0.5%.
    • Numeric Features Modeling: Implemented AutoDis, CTR AUC +0.2% and CVR AUC +0.3%.
  • Techical Reports: 1) Practical Experiences in Rank Model Speed Optimization; 2) Survey of Feature Crosses; 3) Multi-task Modeling; 4) Long Sequence Modeling.

● Recommendation Algorithm Engineering Intern at Alibab, AliExpress
Jun.2021-Sep.2021

As a multinational e-commerce platform, AliExpress needs to pay attention to the behavioral differences of users in different countries. Hence, we designed a country-specific multitask fine-ranking model. During the internship, I reproduced 14 papers and finally adopted PLE, ESMM, and Gradient Block to optimize the multitask framework, designed country-level PLE in the top network to capture the specific information of the top 5 key countries; used DCN-v2 in the bottom network to achieve higher-order feature crossover for country-differentiated features. Results: The fine-ranking results in offline experiments achieved significant improvements in CTR AUC (+0.50%), CTR GAUC (+0.78%), L2P AUC (+0.53%), and L2P GAUC (+1.17%).

● Search Algorithm Engineering Intern at ByteDance
Oct.2018-Mar.2019

Mainly responsible for the official user search in ByteDance’s “Toutiao” series apps (Toutiao, Xigua Video, DongCheDi, etc.), including the vertical search results under the user search tab, and the user card result under the all web search and video search tab. Increase the vertical search query Click-Through-Rate (qCTR: the ratio of clicked queries) under the user tab from the previous 15% to 45% (+30%). Increase the recall rate of user cards under the integrated search and video channels by 60%, and the top 3 user card CTR in the integrated search by 5%.

🏫 Educations

Nanjing University, Computer Science and Technology, School of Artificial Intelligence
2019.09-2022.06
  • In Sep. 2018, I was recommended to be exempted from the postgraduate entrance written examination, and was admitted to enter the LAMDA group with the first place in the coding examination.
Jilin University, Software Engineering (Excellent Engineer Program), School of Software Engineering
2015.09-2019.06
  • GPA (Professional courses): 3.7/ 4.0 (top5%)
  • In the summer of 2017, I went to ITMO University (opens new window) for an exchange study. The main topics are ACM algorithm competition and the fundamentals of machine learning.

📝 Teaching Assistant

📮 Correspondence

Laboratory

Room 516, Yifu Building, Xianlin Campus of Nanjing University

Mail Address

Hui Sun

National Key Laboratory for Novel Software Technology,

Nanjing University, Xianlin Campus Mailbox 603,

163 Xianlin Avenue, Qixia District,

Nanjing 210023, China

Last Updated: 2023/09/01, 11:03:33 PM