A General Recommendation Model for Heterogeneous Networks

摘要: Heterogeneous networks refer to the comprising multiple types of entities as well their interaction relationships. They arise in a great variety domains, for example, event-based social Meetup and Plancast, DBLP. Recommendation is useful task these heterogeneous network systems. Although many recommendation algorithms are proposed data, none them able explicitly model influence strength between different entities, which not only achieving higher accuracy but also better understanding role each entity type problems. Moreover, those designed particular task, hence it challenging apply other In this paper, we propose graph-based model, called HeteRS, can solve general problems on networks. Our method models rich information with graph considers problem query-dependent node proximity problem. To address issue weighting influences learning scheme set weights recommendation. Experimental results real-world datasets demonstrate that our significantly outperforms baseline methods experiments all tasks, learned help user behaviors.