# Rethinking Item Importance in Session-based Recommendation

arXiv: https://arxiv.org/abs/2005.04456 · HTML: https://mlsanity.com/paper/2005.04456/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 May 2020.

## Built on by (most cited first, 7 of 7)

- [Transformers with multi-modal features and post-fusion context for e-commerce session-based recommendation](https://mlsanity.com/paper/2107.05124/) (2021)
- [Session-aware Linear Item-Item Models for Session-based Recommendation](https://mlsanity.com/paper/2103.16104/) (2021)
- [Graph Spring Network and Informative Anchor Selection for Session-based Recommendation](https://mlsanity.com/paper/2202.09502/) (2022)
- [SR-PredictAO: Session-based Recommendation with High-Capability Predictor Add-On](https://mlsanity.com/paper/2309.12218/) (2023)
- [SR-GCL: Session-Based Recommendation with Global Context Enhanced Augmentation in Contrastive Learning](https://mlsanity.com/paper/2209.10807/) (2022)
- [TempGNN: Temporal Graph Neural Networks for Dynamic Session-Based Recommendations](https://mlsanity.com/paper/2310.13249/) (2023)
- [GraphFusionSBR: Denoising Multi-Channel Graphs for Session-Based Recommendation](https://mlsanity.com/paper/2601.08497/) (2026)

## Abstract (arXiv)

Session-based recommendation aims to predict users' based on anonymous sessions. Previous work mainly focuses on the transition relationship between items during an ongoing session. They generally fail to pay enough attention to the importance of the items in terms of their relevance to user's main intent. In this paper, we propose a Session-based Recommendation approach with an Importance Extraction Module, i.e., SR-IEM, that considers both a user's long-term and recent behavior in an ongoing session. We employ a modified self-attention mechanism to estimate item importance in a session, which is then used to predict user's long-term preference. Item recommendations are produced by combining the user's long-term preference and current interest as conveyed by the last interacted item. Experiments conducted on two benchmark datasets validate that SR-IEM outperforms the start-of-the-art in terms of Recall and MRR and has a reduced computational complexity.