Incremental Spatio-Temporal Graph Learning for Online Query-POI Matching
Incremental Spatio-Temporal Graph Learning for Online Query-POI Matching
复制标题
DOI：
10.1145/3442381.3449810
复制
发表时间：
2021-04
期刊：
影响因子：
--
通讯作者：
Zixuan Yuan;Hao Liu;Junming Liu;Yanchi Liu;Yang Yang-Yang;Renjun Hu;Hui Xiong
中科院分区：
文献类型：
--
作者：
Zixuan Yuan;Hao Liu;Junming Liu;Yanchi Liu;Yang Yang-Yang;Renjun Hu;Hui Xiong
查询和兴趣点(POI)匹配旨在从部分查询关键词中推荐最相关的POI，已成为在线导航和叫车应用中最基本的功能之一。现有的查询-POI匹配方法，如Google Maps和Uber，自然侧重于衡量查询的上下文信息和POI的地理信息之间的静态语义相似度。然而，动态和个性化的在线查询-POI匹配仍然具有挑战性，这是因为查询-POI的非静态和情景上下文相关。此外，大量的在线查询需要一种自适应的、增量的模型训练策略，该策略在在线场景中是高效和可扩展的。为此，本文提出了一种用于智能在线查询的增量式时空图学习框架--POI匹配。具体地说，我们首先将动态查询-POI交互建模为微观和宏观图。在此基础上，提出了一个增量图表示学习模块，用于在线增量更新查询-POI交互图，包括：(I)基于动态情境下历史查询量化查询-POI相关性的上下文图注意操作；(Ii)从个性化偏好和社会同质性的整体视角捕捉顺序查询-POI相关性漂移的图鉴别操作；(Iii)多层次时间注意操作，总结查询-POI交互图的时间变化，用于后续的查询-POI匹配。最后，我们介绍了一个轻量级的在线查询语义匹配模块--POI相似度度量。为了验证算法的有效性和效率，我们在中国在线导航和地图服务提供商的两个真实数据集上进行了广泛的实验。
Query and Point-of-Interest (POI) matching, aiming at recommending the most relevant POIs from partial query keywords, has become one of the most essential functions in online navigation and ride-hailing applications. Existing methods for query-POI matching, such as Google Maps and Uber, have a natural focus on measuring the static semantic similarity between contextual information of queries and geographical information of POIs. However, it remains challenging for dynamic and personalized online query-POI matching because of the non-stationary and situational context-dependent query-POI relevance. Moreover, the large volume of online queries requires an adaptive and incremental model training strategy that is efficient and scalable in the online scenario. To this end, in this paper, we propose an Incremental Spatio-Temporal Graph Learning (IncreSTGL) framework for intelligent online query-POI matching. Specifically, we first model dynamic query-POI interactions as microscopic and macroscopic graphs. Then, we propose an incremental graph representation learning module to refine and update query-POI interaction graphs in an online incremental fashion, which includes: (i) a contextual graph attention operation quantifying query-POI correlation based on historical queries under dynamic situational context, (ii) a graph discrimination operation capturing the sequential query-POI relevance drift from a holistic view of personalized preference and social homophily, and (iii) a multi-level temporal attention operation summarizing the temporal variations of query-POI interaction graphs for subsequent query-POI matching. Finally, we introduce a lightweight semantic matching module for online query-POI similarity measurement. To demonstrate the effectiveness and efficiency of the proposed algorithm, we conduct extensive experiments on two real-world datasets collected from a leading online navigation and map service provider in China.