# A Self-Correcting Sequential Recommender

arXiv: https://arxiv.org/abs/2303.02297 · HTML: https://mlsanity.com/paper/2303.02297/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Mar 2023.

## Built on by (most cited first, 9 of 9)

- [FineRec:Exploring Fine-grained Sequential Recommendation](https://mlsanity.com/paper/2404.12975/) (2024)
- [Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendation](https://mlsanity.com/paper/2504.02458/) (2025)
- [Denoising Long- and Short-term Interests for Sequential Recommendation](https://mlsanity.com/paper/2407.14743/) (2024)
- [RAIE: Region-Aware Incremental Preference Editing with LoRA for LLM-based Recommendation](https://mlsanity.com/paper/2603.00638/) (2026)
- [Empowering Denoising Sequential Recommendation with Large Language Model Embeddings](https://mlsanity.com/paper/2510.04239/) (2025)
- [Diversity Augmentation of Dynamic User Preference Data for Boosting Personalized Text Summarizers](https://mlsanity.com/paper/2510.10082/) (2025)
- [Enhancing guidance for missing data in diffusion-based sequential recommendation](https://mlsanity.com/paper/2601.15673/) (2026)
- [ID and Graph View Contrastive Learning with Multi-View Attention Fusion for Sequential Recommendation](https://mlsanity.com/paper/2604.14114/) (2026)
- [Adapting Knowledge Graphs for Behavior Denoising in Sequential Recommendation](https://mlsanity.com/paper/2608.21243/) (2026)

## Abstract (arXiv)

Sequential recommendations aim to capture users' preferences from their historical interactions so as to predict the next item that they will interact with. Sequential recommendation methods usually assume that all items in a user's historical interactions reflect her/his preferences and transition patterns between items. However, real-world interaction data is imperfect in that (i) users might erroneously click on items, i.e., so-called misclicks on irrelevant items, and (ii) users might miss items, i.e., unexposed relevant items due to inaccurate recommendations. To tackle the two issues listed above, we propose STEAM, a Self-correcTing sEquentiAl recoMmender. STEAM first corrects an input item sequence by adjusting the misclicked and/or missed items. It then uses the corrected item sequence to train a recommender and make the next item prediction.We design an item-wise corrector that can adaptively select one type of operation for each item in the sequence. The operation types are 'keep', 'delete' and 'insert.' In order to train the item-wise corrector without requiring additional labeling, we design two self-supervised learning mechanisms: (i) deletion correction (i.e., deleting randomly inserted items), and (ii) insertion correction (i.e., predicting randomly deleted items). We integrate the corrector with the recommender by sharing the encoder and by training them jointly. We conduct extensive experiments on three real-world datasets and the experimental results demonstrate that STEAM outperforms state-of-the-art sequential recommendation baselines. Our in-depth analyses confirm that STEAM benefits from learning to correct the raw item sequences.