Repeated Padding+: Simple yet Effective Data Augmentation Plugin for Sequential Recommendation

Sequential recommendation aims to provide users with personalized suggestions based on their historical interactions. When training sequential models, padding is a widely adopted technique for two main reasons: 1) The vast majority of models can only handle fixed-length sequences; 2) Batching-based training needs to ensure that the sequences in each batch have the same length. The special value \emph{0} is usually used as the padding content, which does not contain the actual information and is ignored in the model calculations. This common-sense padding strategy leads us to a problem that has never been explored before: Can we fully utilize this idle input space by padding other content to further improve model performance and training efficiency? In this work, we propose a simple yet effective padding method called Repeated Padding+ (RepPad+). Specifically, we use the original interaction sequences as the padding content and fill it to the padding positions during model training. This operation can be performed a finite number of times or repeated until the input sequences' length reaches the maximum limit. For those sequences that can not pad full original data, we draw inspiration from the Sliding Windows strategy and intercept consecutive subsequences to fill in the idle space. Our RepPad+ can be viewed as a sequence-level data augmentation strategy. Unlike most existing works, our method contains no trainable parameters or hyperparameters and is a plug-and-play data augmentation operation. Extensive experiments on various categories of sequential models and seven real-world datasets demonstrate the effectiveness and efficiency of our approach. The average recommendation performance improvement is up to 84.11% on GRU4Rec and 35.34% on SASRec. We also provide in-depth analysis and explanation of what makes RepPad+ effective from multiple perspectives.