本文的思想跟 What to Do Next: Modeling User Behaviors by Time-LSTM 很像（应该是借鉴了这篇文章）。
不过在上述文章的基础上（Time + LSTM），增加了另一个信息(Time + Distance + LSTM)，增加的方式同上述引用文章（在一个predefined的向量前面乘以时间或距离间隔）。
另外文章说的variation of coupled input and forget gates可以用来减少模型参数的方法可以借鉴。
| 文献题目 | 去谷歌学术搜索 | ||||||||||
| Where to Go Next: A Spatio-temporal LSTM model for Next POI Recommendation | |||||||||||
| 文献作者 | Pengpeng Zhao; Yanchi Liu | ||||||||||
| 文献发表年限 | 2019 | ||||||||||
| 文献关键字 | |||||||||||
| time interval; distance interval; LSTM; Time-LSTM；减少LSTM参数的方法；CA; SIN; Gowalla; Brightkite | |||||||||||
| 摘要描述 | |||||||||||
| Next Point-of-Interest (POI) recommendation is of great value for both location-based service providers and users. Recently Recurrent Neural Networks (RNNs) have been proved to be effective on sequential recommendation tasks. However, existing RNN solutions rarely consider the spatiotemporal intervals between neighbor check-ins, which are essential for modeling user check-in behaviors in next POI recommendation. In this pa- per, we propose a new variant of LSTM, named ST- LSTM, which implements time gates and distance gates into LSTM to capture the spatiotemporal relation between successive check-ins. Specifically, one-time gate and one distance gate are designed to control short-term interest update, and another time gate and distance gate are designed to control long-term interest update. Furthermore, to reduce the number of parameters and improve efficiency, we further integrate coupled input and forget gates with our proposed model. Finally, we evaluate the proposed model using four real-world datasets from various location-based social networks. Our experimental results show that our model significantly outperforms the state-of-the-art approaches for next POI recommendation. | |||||||||||
