Sequential recommendations have made great strides in accurately predicting the future behaviour of users. However, only persuading accuracy may bring side effects such as unfair and overspecialized recommendation results. From these two perspectives, the calibration of recommendation has gained attention in recent years. It aims to provide fairer recommendations whose preference distributions are consistent with users' historical behaviors. But existing methods relied on the post-processing the candidate lists, which required more computation time and may sacrifice the accuracy. To this end, we propose an end-to-end framework to provide both accurate and calibrated recommendations for sequential recommendation. We design an objective function to calibrate the interests between recommendation lists and historical behaviors. In addition, we design a decoupled-aggregated model which extracts information from two individual sequence encoders with different objectives to further improve the recommendation. Experiments on two benchmark datasets demonstrate the effectiveness and efficiency of our model.

翻译：顺序建议在准确预测用户未来行为方面迈出了长足的步伐。然而,只有说服准确性才能带来一些副作用,如不公平和过于专业化的建议结果。从这两个角度看,建议校准近年来引起了注意。其目的是提供更公平的建议,其偏好分布与用户的历史行为相一致。但现有方法依赖于后处理候选人名单,这需要更多的时间计算,并可能牺牲准确性。为此,我们提议了一个端对端框架,为顺序建议提供准确和校准的建议。我们设计了一个客观功能,以调整建议清单与历史行为之间的利益。此外,我们设计了一个分离的汇总模型,从两个单列序列中提取信息,其目标不同,以进一步改进建议。关于两个基准数据集的实验表明我们模型的有效性和效率。