Augmenting Sequential Recommendation with Pseudo-Prior Items via Reversely Pre-training Transformer

TL;DR

This paper introduces ASReP, a framework that enhances short sequence recommendation by generating pseudo-prior items through reverse pre-training of transformers, improving performance on cold-start sequences.

Contribution

It proposes a novel reverse pre-training method to generate pseudo-prior items, effectively augmenting short sequences for better sequential recommendation.

Findings

ASReP outperforms baseline models on real-world datasets.

The reverse pre-training improves cold-start sequence handling.

Augmentation with pseudo-prior items enhances recommendation accuracy.

Abstract

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}.