In this paper, we propose a novel sequence-aware recommendation model. Our model utilizes self-attention mechanism to infer the item-item relationship from user's historical interactions. With self-attention, it is able to estimate the relative weights of each item in user interaction trajectories to learn better representations for user's transient interests. The model is finally trained in a metric learning framework, taking both short-term and long-term intentions into consideration. Experiments on a wide range of datasets on different domains demonstrate that our approach outperforms the state-of-the-art by a wide margin.
@article{arxiv.1808.06414,
title = {Next Item Recommendation with Self-Attention},
author = {Shuai Zhang and Yi Tay and Lina Yao and Aixin Sun},
journal= {arXiv preprint arXiv:1808.06414},
year = {2018}
}