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

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}.

arXiv commentAccepted by SIGIR 2021

References in corpus (4)

• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization
• Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks
• Sequential Recommendation with Self-Attentive Multi-Adversarial Network

Cited by in corpus (9)

• LinRec: Linear Attention Mechanism for Long-term Sequential Recommender Systems
• Large-scale Personalized Video Game Recommendation via Social-aware Contextualized Graph Neural Network
• MELT: Mutual Enhancement of Long-Tailed User and Item for Sequential Recommendation
• A Comprehensive Survey on Self-Supervised Learning for Recommendation
• Improving Conversational Recommendation Systems via Counterfactual Data Simulation
• Contrastive Learning on Medical Intents for Sequential Prescription Recommendation
• Temporal Interest Network for User Response Prediction
• Enhancing Transformers without Self-supervised Learning: A Loss Landscape Perspective in Sequential Recommendation
• TD3: Tucker Decomposition Based Dataset Distillation Method for Sequential Recommendation