针对传统的群组推荐预定义策略过于单一,忽视用户与项目之间的交互性,无法捕捉时间推移所造成的用户偏好迁移等问题,提出一种融合时间序列和注意力机制的群组推荐模型TAGR(time-attitation group rememdation).首先通过层次聚类划分出高相似度群组,其次引入时间序列模型来捕捉用户偏好迁移过程,获取每个时刻用户行为的兴趣偏好,并聚合各时刻兴趣偏好作为用户偏好.最后结合注意力机制,获得用户权重进行偏好融合来表示群组偏好,最终作为推荐模型的输入.通过在Goodbook与MovieLens数据集上与 NCF、AGREE 等模型进行对比,TAGR在归一化折扣累计增益和命中率2个指标上都得到了显著提高.
A group recommendation model integrating time series features
Traditional group recommendation has such problems as ineffective predefined strate-gy,neglect of the interaction between users and projects,and failure to capture the migration of user preferences caused by the passage of time.In response to the above problems,a group rec-ommendation model TAGR(time-attentive group recommendation)that integrates time series and attention mechanisms was proposed.Firstly,high similarity groups were divided through hi-erarchical clustering.Secondly,a time series model was introduced to capture the process of user preference transfer,obtain the interest preferences of user behavior at each moment,and aggre-gate the interest preferences at each moment as user preferences.Finally,with attention mecha-nism,user weights were obtained for preference fusion to represent group preferences,serving as the input of the recommendation model.By comparing with NCF,AGREE and other models on the Goodbook and MovieLens datasets,the proposed model TAGR has been significantly im-proved in both normalized discount cumulative gain and hit rate.
group recommendationtime serieshierarchical clusteringneural networkattention mechanism
国家科技期刊平台
NSTL
万方数据
维普
