With the development of location-based services (LBS), many location-based social sites like Foursquare and Plancast have emerged. People can organize and participate in group activities on those sites. Therefore, recommending venues for group activities is of practical value. However, the group decision making process is complicated, requiring trade-offs among group members. And the data sparsity and cold-start problems make it difficult to make effective group recommendation. In this manuscript, we propose a Multi-view Group Representation Learning (MGPL) framework for location-aware group recommendation. The proposed multi-view group representation learning framework can leverage multiple types of information for deep representation learning of group preferences and incorporate the spatial attributes of locations to further capture the group mobility preferences. Experiments on two real datasets Foursqaure and Plancast show that our method significantly outperforms the-state-of-art approaches.

随着基于位置的服务（LBS）的发展，出现了许多基于位置的社交网站，如 Foursquare 和 Plancast。人们可以在这些网站上组织和参与集体活动。因此，为团体活动推荐场地具有实用价值。然而，群体决策过程复杂，需要群体成员之间的权衡。并且数据稀疏性和冷启动问题使得难以进行有效的群组推荐。在这份手稿中，我们提出了一种用于位置感知组推荐的多视图组表示学习 (MGPL) 框架。所提出的多视图组表示学习框架可以利用多种类型的信息进行组偏好的深度表示学习，并结合位置的空间属性来进一步捕捉组移动性偏好。在两个真实数据集 Foursqaure 和 Plancast 上的实验表明，我们的方法明显优于最先进的方法。