RCLRec: Reverse Curriculum Learning for Modeling Sparse Conversions in Generative Recommendation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917368662327296 |
|---|---|
| author | Huang, Yulei Deng, Hao Xing, Haibo Hu, Jinxin Xu, Chuanfei Chen, Zulong Zhang, Yu Zeng, Xiaoyi |
| author_facet | Huang, Yulei Deng, Hao Xing, Haibo Hu, Jinxin Xu, Chuanfei Chen, Zulong Zhang, Yu Zeng, Xiaoyi |
| contents | Conversion objectives in large-scale recommender systems are sparse, making them difficult to optimize. Generative recommendation (GR) partially alleviates data sparsity by organizing multi-type behaviors into a unified token sequence with shared representations, but conversion signals remain insufficiently modeled. While recent behavior-aware GR models encode behavior types and employ behavior-aware attention to highlight decision-related intermediate behaviors, they still rely on standard attention over the full history and provide no additional supervision for conversions, leaving conversion sparsity largely unresolved. To address these challenges, we propose RCLRec, a reverse curriculum learning-based GR framework for sparse conversion supervision. For each conversion target, RCLRec constructs a short curriculum by selecting a subsequence of conversion-related items from the history in reverse. Their semantic tokens are fed to the decoder as a prefix, together with the target conversion tokens, under a joint generation objective. This design provides additional instance-specific intermediate supervision, alleviating conversion sparsity and focusing the model on the user's critical decision process. We further introduce a curriculum quality-aware loss to ensure that the selected curricula are informative for conversion prediction. Experiments on offline datasets and an online A/B test show that RCLRec achieves superior performance, with +2.09% advertising revenue and +1.86% orders in online deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_28124 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RCLRec: Reverse Curriculum Learning for Modeling Sparse Conversions in Generative Recommendation Huang, Yulei Deng, Hao Xing, Haibo Hu, Jinxin Xu, Chuanfei Chen, Zulong Zhang, Yu Zeng, Xiaoyi Information Retrieval Conversion objectives in large-scale recommender systems are sparse, making them difficult to optimize. Generative recommendation (GR) partially alleviates data sparsity by organizing multi-type behaviors into a unified token sequence with shared representations, but conversion signals remain insufficiently modeled. While recent behavior-aware GR models encode behavior types and employ behavior-aware attention to highlight decision-related intermediate behaviors, they still rely on standard attention over the full history and provide no additional supervision for conversions, leaving conversion sparsity largely unresolved. To address these challenges, we propose RCLRec, a reverse curriculum learning-based GR framework for sparse conversion supervision. For each conversion target, RCLRec constructs a short curriculum by selecting a subsequence of conversion-related items from the history in reverse. Their semantic tokens are fed to the decoder as a prefix, together with the target conversion tokens, under a joint generation objective. This design provides additional instance-specific intermediate supervision, alleviating conversion sparsity and focusing the model on the user's critical decision process. We further introduce a curriculum quality-aware loss to ensure that the selected curricula are informative for conversion prediction. Experiments on offline datasets and an online A/B test show that RCLRec achieves superior performance, with +2.09% advertising revenue and +1.86% orders in online deployment. |
| title | RCLRec: Reverse Curriculum Learning for Modeling Sparse Conversions in Generative Recommendation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2603.28124 |