一作SIGIR 2026Poster· Information Retrieval (Short)
RCLRec: Reverse Curriculum Learning for Modeling Sparse Conversions in Generative Recommendation
Yulei Huang · Hao Deng · Haibo Xing · Jinxin Hu · Chuanfei Xu · Zulong Chen · Yu Zhang · Xiaoyi Zeng
摘要
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 ins...