Sequential recommenders are crucial to the success of online applications, \eg e-commerce, video streaming, and social media. While model architectures continue to improve, for every new application domain, we still have to train a new model from scratch for high quality recommendations. On the other hand, pre-trained language and vision models have shown great success in zero-shot or few-shot adaptation to new application domains. Inspired by the success of pre-trained models in peer AI fields, we propose a novel pre-trained sequential recommendation framework: PrepRec. We learn universal item representations by modeling item popularity dynamics. Through extensive experiments on five real-world datasets, we show that PrepRec, without any auxiliary information, can not only zero-shot transfer to a new domain, but achieve competitive performance compared to state-of-the-art sequential recommender models with only a fraction of the model size. In addition, with a simple post-hoc interpolation, PrepRec can improve the performance of existing sequential recommenders on average by 13.8\% in Recall@10 and 29.5% in NDCG@10. We provide an anonymized implementation of PrepRec at https://anonymous.4open.science/r/PrepRec--2F60/

翻译：序列推荐器对于在线应用（例如电子商务、视频流媒体和社交媒体）的成功至关重要。尽管模型架构持续改进，但对于每个新的应用领域，我们仍需从头训练一个新模型以实现高质量推荐。另一方面，预训练的语言和视觉模型在零样本或小样本适应新应用领域方面已展现出巨大成功。受预训练模型在人工智能领域成功经验的启发，我们提出了一种新颖的预训练序列推荐框架：PrepRec。我们通过建模物品流行度动态来学习通用物品表征。通过在五个真实世界数据集上进行广泛实验，我们证明PrepRec无需任何辅助信息，不仅能零样本迁移到新领域，还能以极小的模型尺寸取得与最先进序列推荐模型相媲美的性能。此外，通过简单的后验插值，PrepRec可平均提升现有序列推荐器在Recall@10上13.8%和在NDCG@10上29.5%的性能。我们在https://anonymous.4open.science/r/PrepRec--2F60/ 提供了PrepRec的匿名化实现。