Chengkai Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chengkai Liu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- James Caverlee
Texas A&M University, College Station, USA
2 shared publications - Jianling Wang
Google DeepMind, Mountain View, CA, USA
2 shared publications - Hanzhou Liu
Texas A&M University, College Station, TX, USA
1 shared publication - Jianghao Lin
Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Rex Ying
Yale University, New Haven, CT, USA
1 shared publication - Yangtian Zhang
Yale University, New Haven, Connecticut, USA
1 shared publication
Latest Publications
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1765-1775
Flow Matching for Collaborative Filtering
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1765-1775
Open AccessFlow Matching for Collaborative Filtering
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1430-1440
Behavior-Dependent Linear Recurrent Units for Efficient Sequential Recommendation
Sequential recommender systems aims to predict the users' next interaction through user behavior modeling with various operators like RNNs and attentions. However, existing models generally fail to achieve the three golden principles for sequential recommendation simultaneously, i.e., training efficiency, low-cost inference, and strong performance. To this end, we propose RecBLR, an Efficient Sequential Recommendation Model based on Behavior-Dependent Linear Recurrent Units to accomplish the impossible triangle of the three principles. By incorporating gating mechanisms and behavior-dependent designs into linear recurrent units, our model significantly enhances user behavior modeling and recommendation performance. Furthermore, we unlock the parallelizable training as well as inference efficiency for our model by designing a hardware-aware scanning acceleration algorithm with a customized CUDA kernel. Extensive experiments on real-world datasets with varying lengths of user behavior sequences demonstrate RecBLR's remarkable effectiveness in simultaneously achieving all three golden principles - strong recommendation performance, training efficiency, and low-cost inference, while exhibiting excellent scalability to datasets with long user interaction histories.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1430-1440
Open AccessBehavior-Dependent Linear Recurrent Units for Efficient Sequential Recommendation
Sequential recommender systems aims to predict the users' next interaction through user behavior modeling with various operators like RNNs and attentions. However, existing models generally fail to achieve the three golden principles for sequential recommendation simultaneously, i.e., training efficiency, low-cost inference, and strong performance. To this end, we propose RecBLR, an Efficient Sequential Recommendation Model based on Behavior-Dependent Linear Recurrent Units to accomplish the impossible triangle of the three principles. By incorporating gating mechanisms and behavior-dependent designs into linear recurrent units, our model significantly enhances user behavior modeling and recommendation performance. Furthermore, we unlock the parallelizable training as well as inference efficiency for our model by designing a hardware-aware scanning acceleration algorithm with a customized CUDA kernel. Extensive experiments on real-world datasets with varying lengths of user behavior sequences demonstrate RecBLR's remarkable effectiveness in simultaneously achieving all three golden principles - strong recommendation performance, training efficiency, and low-cost inference, while exhibiting excellent scalability to datasets with long user interaction histories.