Beichuan Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Beichuan Zhang has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Hangyu Wang
ByteDance, Shanghai, China
2 shared publications - Jia-Qi Yang
ByteDance, Shanghai, China
2 shared publications - Jinan Ni
ByteDance, Shanghai, China
2 shared publications - Lin Guan
Bytedance, Beijing, China
2 shared publications - Na Mou
Kuaishou, Beijing, China
2 shared publications - Qiwei Chen
ByteDance, Shanghai, China
2 shared publications
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1471-1480
SequenceO1: End-to-End Ultra-Long (100K) Sequence Modeling in Recommendation with Low-Rank Caching
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1471-1480
Open AccessSequenceO1: End-to-End Ultra-Long (100K) Sequence Modeling in Recommendation with Low-Rank Caching
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 7989-7998
Make It Long, Keep It Fast: End-to-End 10k-Sequence Modeling at Billion Scale on Douyin
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 7989-7998
Open AccessMake It Long, Keep It Fast: End-to-End 10k-Sequence Modeling at Billion Scale on Douyin
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 3621-3631
Full Stage Learning to Rank: A Unified Framework for Multi-Stage Systems
The Probability Ranking Principle (PRP) has been considered as the foundational standard in the design of information retrieval (IR) systems. The principle requires an IR module's returned list of results to be ranked with respect to the underlying user interests, so as to maximize the results' utility. Nevertheless, we point out that it is inappropriate to indiscriminately apply PRP through every stage of a contemporary IR system. Such systems contain multiple stages (e.g., retrieval, pre-ranking, ranking, and re-ranking stages, as examined in this paper). The selection bias inherent in the model of each stage significantly influences the results that are ultimately presented to users. To address this issue, we propose an improved ranking principle for multi-stage systems, namely the Generalized Probability Ranking Principle (GPRP), to emphasize both the selection bias in each stage of the system pipeline as well as the underlying interest of users. We realize GPRP via a unified algorithmic framework named Full Stage Learning to Rank. Our core idea is to first estimate the selection bias in the subsequent stages and then learn a ranking model that best complies with the downstream modules' selection bias so as to deliver its top ranked results to the final ranked list in the system's output. We performed extensive experiment evaluations of our developed Full Stage Learning to Rank solution, using both simulations and online A/B tests in one of the leading short-video recommendation platforms. The algorithm is proved to be effective in both retrieval and ranking stages. Since deployed, the algorithm has brought consistent and significant performance gain to the platform.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 3621-3631
Open AccessFull Stage Learning to Rank: A Unified Framework for Multi-Stage Systems
The Probability Ranking Principle (PRP) has been considered as the foundational standard in the design of information retrieval (IR) systems. The principle requires an IR module's returned list of results to be ranked with respect to the underlying user interests, so as to maximize the results' utility. Nevertheless, we point out that it is inappropriate to indiscriminately apply PRP through every stage of a contemporary IR system. Such systems contain multiple stages (e.g., retrieval, pre-ranking, ranking, and re-ranking stages, as examined in this paper). The selection bias inherent in the model of each stage significantly influences the results that are ultimately presented to users. To address this issue, we propose an improved ranking principle for multi-stage systems, namely the Generalized Probability Ranking Principle (GPRP), to emphasize both the selection bias in each stage of the system pipeline as well as the underlying interest of users. We realize GPRP via a unified algorithmic framework named Full Stage Learning to Rank. Our core idea is to first estimate the selection bias in the subsequent stages and then learn a ranking model that best complies with the downstream modules' selection bias so as to deliver its top ranked results to the final ranked list in the system's output. We performed extensive experiment evaluations of our developed Full Stage Learning to Rank solution, using both simulations and online A/B tests in one of the leading short-video recommendation platforms. The algorithm is proved to be effective in both retrieval and ranking stages. Since deployed, the algorithm has brought consistent and significant performance gain to the platform.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4930-4937
SHARK: A Lightweight Model Compression Approach for Large-scale Recommender Systems
Increasing the size of embedding layers has shown to be effective in improving the performance of recommendation models, yet gradually causing their sizes to exceed terabytes in industrial recommender systems, and hence the increase of computing and storage costs. To save resources while maintaining model performances, we propose SHARK, the model compression practice we have summarized in the recommender system of industrial scenarios. SHARK consists of two main components. First, we use the novel first-order component of Taylor expansion as importance scores to prune the number of embedding tables (feature fields). Second, we introduce a new row-wise quantization method to apply different quantization strategies to each embedding. We conduct extensive experiments on both public and industrial datasets, demonstrating that each component of our proposed SHARK framework outperforms previous approaches. We conduct A/B tests in multiple models on Kuaishou, such as short video, e-commerce, and advertising recommendation models. The results of the online A/B test showed SHARK can effectively reduce the memory footprint of the embedded layer. For the short-video scenarios, the compressed model without any performance drop significantly saves 70% storage and thousands of machines, improves 30% queries per second (QPS), and has been deployed to serve hundreds of millions of users and process tens of billions of requests every day.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4930-4937
Open AccessSHARK: A Lightweight Model Compression Approach for Large-scale Recommender Systems
Increasing the size of embedding layers has shown to be effective in improving the performance of recommendation models, yet gradually causing their sizes to exceed terabytes in industrial recommender systems, and hence the increase of computing and storage costs. To save resources while maintaining model performances, we propose SHARK, the model compression practice we have summarized in the recommender system of industrial scenarios. SHARK consists of two main components. First, we use the novel first-order component of Taylor expansion as importance scores to prune the number of embedding tables (feature fields). Second, we introduce a new row-wise quantization method to apply different quantization strategies to each embedding. We conduct extensive experiments on both public and industrial datasets, demonstrating that each component of our proposed SHARK framework outperforms previous approaches. We conduct A/B tests in multiple models on Kuaishou, such as short video, e-commerce, and advertising recommendation models. The results of the online A/B test showed SHARK can effectively reduce the memory footprint of the embedded layer. For the short-video scenarios, the compressed model without any performance drop significantly saves 70% storage and thousands of machines, improves 30% queries per second (QPS), and has been deployed to serve hundreds of millions of users and process tens of billions of requests every day.