Repeated Padding for Sequential Recommendation
Open Access
- 8 October 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 497-506
Abstract
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) Batch-based training needs to ensure that the sequences in each batch have the same length. The special value 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 in the recommendation field: Can we utilize this idle input space by padding other content to improve model performance and training efficiency further? In this paper, 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. Our RepPad can be considered 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 five real-world datasets demonstrate the effectiveness and efficiency of our approach. The average recommendation performance improvement is up to 60.3% on GRU4Rec and 24.3% on SASRec. We also provide in-depth analysis and explanation of what makes RepPad effective from multiple perspectives. Our datasets and codes are available at https://github.com/KingGugu/RepPad.Keywords
Funding Information
- Science and Technology Projects in Liaoning Province (2023JH3/10200005)
- Fundamental Research Funds for the Central Universities (N2317002)
- National Natural Science Foundation of China (62032013)
This publication has 19 references indexed in Scilit:
- Cross-Domain Recommendation via Progressive Structural AlignmentIEEE Transactions on Knowledge and Data Engineering, 2023
- Counterfactual Data-Augmented Sequential Recommendation2021
- On Sampled Metrics for Item Recommendation2020
- BERT4Rec2019
- A Simple Convolutional Generative Network for Next Item Recommendation2019
- Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding2018
- Improved Recurrent Neural Networks for Session-based Recommendations2016
- Inferring Networks of Substitutable and Complementary Products2015
- Factorizing personalized Markov chains for next-basket recommendation2010
- Bidirectional recurrent neural networksIEEE Transactions on Signal Processing, 1997