arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.10983cs.IRcs.AIcs.LG
收藏

在线POI建议:学习流中的动态地人交互

Online POI Recommendation: Learning Dynamic Geo-Human Interactions in Streams

University of Central Florida(中佛罗里达大学);Portland State University(波特兰州立大学);Rutgers University(罗格斯大学)

Dongjie Wang, Kunpeng Liu, Hui Xiong, Yanjie Fu

摘要:

在本文中,我们专注于问题的建模动态地理人类互动流在线POI建议。具体来说,我们制定了流中的地理人类交互建模问题到一个新的深度交互式强化学习框架,其中代理是一个推荐和行动是下一个POI访问。我们独特地将强化学习环境建模为用户和地理空间上下文(POI,POI类别,功能区)的联合和连接组成。用户访问流中的POI的事件更新用户和地理空间上下文的状态;代理感知更新的环境状态以进行在线推荐。具体来说,我们通过将所有用户、访问和地理空间上下文统一为动态知识图谱流来建模混合用户事件流,以建模人-人、地理-人、地理-地理交互。我们设计了一个退出机制来解决过期信息的挑战,设计了一个元路径方法来解决推荐候选生成的挑战,并开发了一个新的深度策略网络结构来解决不断变化的动作空间的挑战,最后,提出了一个有效的对抗训练方法进行优化。最后,我们提出了广泛的实验来证明我们的方法的增强性能。

英文摘要:

In this paper, we focus on the problem of modeling dynamic geo-human interactions in streams for online POI recommendations. Specifically, we formulate the in-stream geo-human interaction modeling problem into a novel deep interactive reinforcement learning framework, where an agent is a recommender and an action is a next POI to visit. We uniquely model the reinforcement learning environment as a joint and connected composition of users and geospatial contexts (POIs, POI categories, functional zones). An event that a user visits a POI in stream updates the states of both users and geospatial contexts; the agent perceives the updated environment state to make online recommendations. Specifically, we model a mixed-user event stream by unifying all users, visits, and geospatial contexts as a dynamic knowledge graph stream, in order to model human-human, geo-human, geo-geo interactions. We design an exit mechanism to address the expired information challenge, devise a meta-path method to address the recommendation candidate generation challenge, and develop a new deep policy network structure to address the varying action space challenge, and, finally, propose an effective adversarial training method for optimization. Finally, we present extensive experiments to demonstrate the enhanced performance of our method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑