sequential recommendation (SR) models user dynamics and predicts the next
preferred items based on the user history. Existing SR methods model the 'was
interacted before' item-item transitions observed in sequences, which can be
viewed as an item relationship. However, there are multip
该论文提出了一种基于多模态信息的多模态预训练和迁移学习框架(MISSRec),用于顺序推荐,以解决现有基于 ID 特征的推荐方法在稀疏 ID 和冷启动问题方面的性能不佳的问题。通过在用户和候选项两方面分别设计 Transformer-based 的编码器 - 解码器模型和动态融合模块,MISSRec 能够实现更鲁棒且可迁移的序列表示,该方法在实验中表现出的效果和灵活性使其成为实际推荐场景的可行解决方案。