SL4SR: Selective Learning for Sequential Recommendation

Recent advances in deep learning have substantially improved sequential recommendation (SR) by enabling more expressive architectures to capture complex user behavior patterns. However, the increased model capacity can also make SR models more prone to fitting incidental, transient, or weakly informative interactions that are less generalizable to future user preferences. This issue is further amplified by the prevailing training paradigm in SR, where standard objectives typically treat all training instances uniformly, regardless of their usefulness for improving the current model. To address this limitation, we propose $\text{SL4SR}$, a simple and effective $\text{S}$elective $\text{L}$earning framework for $\text{S}$equential $\text{R}$ecommendation. SL4SR leverages a pre-trained estimator as a reference model and compares its sample-wise loss with that of the current backbone to estimate the learning utility of each training instance. Based on this estimator-guided score, the model selectively updates on informative high-score instances while filtering out instances that are less likely to improve generalization. The proposed framework is model-agnostic and introduces no additional inference overhead. Extensive experiments on six real-world datasets with four representative SR backbones demonstrate the effectiveness of SL4SR, yielding average improvements of 16.97%, 17.65%, 17.07%, and 4.85% for SASRec, GRU4Rec, FMLPRec, and Mamba4Rec, respectively.