DACSR: Decoupled-Aggregated End-to-End Calibrated Sequential Recommendation

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.