Yankai Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yankai Wang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Defu Lian
University of Science and Technology of China, Hefei, China
2 shared publications - Xingmei Wang
University of Science and Technology of China, Hefei, China
2 shared publications - Enhong Chen
University of Science and Technology of China
1 shared publication - Haoran Jin
University of Science and Technology of China, Hefei, China
1 shared publication - Jin Chen
Tencent Inc., Shenzhen, China
1 shared publication - Le Wu
Hefei University of Technology
1 shared publication
Latest Publications
- Open Access
- 19 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 14-17
A Simple and Robust Ensemble For Click-Through Rate Prediction
This paper presents the strategy employed by the TOT team, which secured 3rd place in the ACM RecSys Challenge 2023 among academic teams. The challenge, orchestrated by ShareChat, focuses on online advertising and user privacy. The objective is to predict the probability of an application install for each anonymized entry. Our approach, though simple, proves efficient and comprises two primary components: initially, we explore state-of-the-art single-task and multi-task models, and subsequently, we integrate these via a simple yet robust ensemble.
- 19 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 14-17
Open AccessA Simple and Robust Ensemble For Click-Through Rate Prediction
This paper presents the strategy employed by the TOT team, which secured 3rd place in the ACM RecSys Challenge 2023 among academic teams. The challenge, orchestrated by ShareChat, focuses on online advertising and user privacy. The objective is to predict the probability of an application install for each anonymized entry. Our approach, though simple, proves efficient and comprises two primary components: initially, we explore state-of-the-art single-task and multi-task models, and subsequently, we integrate these via a simple yet robust ensemble.
- Open Access
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 2890-2900
RecStudio: Towards a Highly-Modularized Recommender System
A dozen recommendation libraries have recently been developed to accommodate popular recommendation algorithms for reproducibility. However, they are almost simply a collection of algorithms, overlooking the modularization of recommendation algorithms and their usage in practical scenarios. Algorithmic modularization has the following advantages: 1) helps to understand the effectiveness of each algorithm; 2) easily assembles new algorithms with well-performed modules by either drag-and-drop programming or automatic machine learning; 3) enables reinforcement between algorithms since one algorithm may act as a module of another algorithm. To this end, we develop a highly-modularized recommender system -- RecStudio, in which any recommendation algorithm is categorized into either a ranker or a retriever. In the RecStudio library, we implement 90 recommendation algorithms with the pure Pytorch, covering both common algorithms in other libraries and complex algorithms involving multiple recommendation models. RecStudio is featured from several perspectives, such as index-supported efficient recommendation and evaluation, GPU-accelerated negative sampling, hyperparameter learning on the validation, and cooperation between the retriever and ranker. RecStudio is also equipped with a web service, where the recommendation pipeline can be quickly established and visually evaluated on selected datasets, and the evaluation results are automatically archived and visualized in a leaderboard. The project and documents are released at http://recstudio.org.cn.
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 2890-2900
Open AccessRecStudio: Towards a Highly-Modularized Recommender System
A dozen recommendation libraries have recently been developed to accommodate popular recommendation algorithms for reproducibility. However, they are almost simply a collection of algorithms, overlooking the modularization of recommendation algorithms and their usage in practical scenarios. Algorithmic modularization has the following advantages: 1) helps to understand the effectiveness of each algorithm; 2) easily assembles new algorithms with well-performed modules by either drag-and-drop programming or automatic machine learning; 3) enables reinforcement between algorithms since one algorithm may act as a module of another algorithm. To this end, we develop a highly-modularized recommender system -- RecStudio, in which any recommendation algorithm is categorized into either a ranker or a retriever. In the RecStudio library, we implement 90 recommendation algorithms with the pure Pytorch, covering both common algorithms in other libraries and complex algorithms involving multiple recommendation models. RecStudio is featured from several perspectives, such as index-supported efficient recommendation and evaluation, GPU-accelerated negative sampling, hyperparameter learning on the validation, and cooperation between the retriever and ranker. RecStudio is also equipped with a web service, where the recommendation pipeline can be quickly established and visually evaluated on selected datasets, and the evaluation results are automatically archived and visualized in a leaderboard. The project and documents are released at http://recstudio.org.cn.