Behavior-Dependent Linear Recurrent Units for Efficient Sequential Recommendation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909307217379328 |
|---|---|
| author | Liu, Chengkai Lin, Jianghao Liu, Hanzhou Wang, Jianling Caverlee, James |
| author_facet | Liu, Chengkai Lin, Jianghao Liu, Hanzhou Wang, Jianling Caverlee, James |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_12580 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Behavior-Dependent Linear Recurrent Units for Efficient Sequential Recommendation Liu, Chengkai Lin, Jianghao Liu, Hanzhou Wang, Jianling Caverlee, James Information Retrieval 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. |
| title | Behavior-Dependent Linear Recurrent Units for Efficient Sequential Recommendation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2406.12580 |