Liyin Hong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Liyin Hong has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Boyang Xia
Kuaishou Technology, Beijing, China
1 shared publication - Guorui Zhou
Kuaishou Technology, Beijing, China
1 shared publication - Jiaming Zhang
Kuaishou Technology, Beijing, China
1 shared publication - Jiangxia Cao
Kuaishou Technology, Beijing, China
1 shared publication - Jingcheng Zhang
Kuaishou Technology, Beijing, China
1 shared publication - Junlin He
Kuaishou Technology, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1030-1038
ConAlign: Conditional Alignment Framework for Balancing Biased and Unbiased Recommendation
Industry recommender systems trained on observational data suffer from various biases that create filter bubbles, causing user interests to collapse into narrow categories and severely degrading long-term engagement. While utilizing unbiased uniform data for debiasing has shown promise, existing methods remain impractical for industrial deployment due to limitations such as neglect of factual (biased) recommendation performance and the substantial computational overhead. To overcome these limitations, we propose ConAlign (Conditional Alignment Framework), a conditional debiasing approach for industrial deployment. The key innovation of ConAlign lies in a discrete gating-based conditional alignment mechanism that selectively transfers knowledge from the biased tower to the unbiased tower. Following a selective intervention paradigm rather than universal correction, it seamlessly balances factual accuracy and unbiased preference estimation while supporting real-time streaming adaptation. To the best of our knowledge, ConAlign is the first streaming debiasing recommendation framework successfully deployed in a large-scale industrial recommendation system that utilizes a small fraction of unbiased random traffic for debiasing. Extensive offline experiments on three real-world datasets rigorously validate the effectiveness of our proposed framework4. Furthermore, large-scale online A/B testing on Kuaishou demonstrates significant improvements in long-term user engagement and interest diversity, with negligible latency overhead.
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1030-1038
Open AccessConAlign: Conditional Alignment Framework for Balancing Biased and Unbiased Recommendation
Industry recommender systems trained on observational data suffer from various biases that create filter bubbles, causing user interests to collapse into narrow categories and severely degrading long-term engagement. While utilizing unbiased uniform data for debiasing has shown promise, existing methods remain impractical for industrial deployment due to limitations such as neglect of factual (biased) recommendation performance and the substantial computational overhead. To overcome these limitations, we propose ConAlign (Conditional Alignment Framework), a conditional debiasing approach for industrial deployment. The key innovation of ConAlign lies in a discrete gating-based conditional alignment mechanism that selectively transfers knowledge from the biased tower to the unbiased tower. Following a selective intervention paradigm rather than universal correction, it seamlessly balances factual accuracy and unbiased preference estimation while supporting real-time streaming adaptation. To the best of our knowledge, ConAlign is the first streaming debiasing recommendation framework successfully deployed in a large-scale industrial recommendation system that utilizes a small fraction of unbiased random traffic for debiasing. Extensive offline experiments on three real-world datasets rigorously validate the effectiveness of our proposed framework4. Furthermore, large-scale online A/B testing on Kuaishou demonstrates significant improvements in long-term user engagement and interest diversity, with negligible latency overhead.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7358-7366
Breaking the Listwise-Shuffle Dilemma: A Streaming-Compatible Listwise Framework for Industrial CTR Prediction
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7358-7366
Open AccessBreaking the Listwise-Shuffle Dilemma: A Streaming-Compatible Listwise Framework for Industrial CTR Prediction
- Top Cited PapersOpen Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1115-1119
ChorusCVR: Chorus Supervision for Entire Space Post-Click Conversion Rate Modeling
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1115-1119
Top Cited PapersOpen AccessChorusCVR: Chorus Supervision for Entire Space Post-Click Conversion Rate Modeling