Group event recommendation based on graph multi-head attention network combining explicit and implicit information

•We establish a general group event recommendation framework in EBSN.•We alleviate the problem of sparse data in group recommendation and solve the problem of learning vector redundancy.•We produce better user and event vector representations by using the multi-head attention mechanism.•Experimental results on two real-world datasets demonstrate that the proposed model significantly outperforms state-of-the-art methods on group event recommendation.