基于Reason预训练Transformer的伪先验序列推荐算法
Augmenting Sequential Recommendation with Pseudo-Prior Items via Reversely Pre-training Transformer
摘要：
顺序推荐通过按时间顺序对项目序列进行建模来表征不断演化的模式。它的基本目标是捕捉项目转换相关性。Transformer的最新发展启发了社区设计有效的序列编码器，\textit{e.g.,} SASRec和BERT 4 Rec。然而，我们观察到这些基于transformer的模型存在冷启动问题，\textit{i.e.,}对于短序列表现不佳。因此，我们建议增加短序列，同时仍然保留原始的序列相关性。本文提出了一种新的\textbf{A}算法框架，它利用\textbf{P}的先验项~（ASReP）对\textbf{S}序列\textbf{Re}进行推荐。我们首先用反向序列预训练一个Transformer，以预测先前的项目。然后，我们使用这个Transformer在短序列的开头生成虚构的历史项。最后，我们使用这些来自时间顺序的增强序列来微调Transformer以预测下一项。在两个真实数据集上的实验验证了ASReP的有效性。代码可在\url{https://github.com/DyGRec/ASReP}上获得。
英文摘要：
Sequential Recommendation characterizes the evolving patterns by modeling item sequences chronologically. The essential target of it is to capture the item transition correlations. The recent developments of transformer inspire the community to design effective sequence encoders, \textit{e.g.,} SASRec and BERT4Rec. However, we observe that these transformer-based models suffer from the cold-start issue, \textit{i.e.,} performing poorly for short sequences. Therefore, we propose to augment short sequences while still preserving original sequential correlations. We introduce a new framework for \textbf{A}ugmenting \textbf{S}equential \textbf{Re}commendation with \textbf{P}seudo-prior items~(ASReP). We firstly pre-train a transformer with sequences in a reverse direction to predict prior items. Then, we use this transformer to generate fabricated historical items at the beginning of short sequences. Finally, we fine-tune the transformer using these augmented sequences from the time order to predict the next item. Experiments on two real-world datasets verify the effectiveness of ASReP. The code is available on \url{https://github.com/DyGRec/ASReP}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
