CORE: Simple and Effective Session-based Recommendation within Consistent Representation Space

TL;DR

CORE introduces a simple framework for session-based recommendation that ensures session and item embeddings are in the same space, improving prediction consistency and model robustness.

Contribution

The paper proposes a linear combination-based session encoder and a robust distance measure to unify representation space and enhance recommendation accuracy.

Findings

Effective on five real-world datasets

Improves prediction consistency

Reduces overfitting in embeddings

Abstract

Session-based Recommendation (SBR) refers to the task of predicting the next item based on short-term user behaviors within an anonymous session. However, session embedding learned by a non-linear encoder is usually not in the same representation space as item embeddings, resulting in the inconsistent prediction issue while recommending items. To address this issue, we propose a simple and effective framework named CORE, which can unify the representation space for both the encoding and decoding processes. Firstly, we design a representation-consistent encoder that takes the linear combination of input item embeddings as session embedding, guaranteeing that sessions and items are in the same representation space. Besides, we propose a robust distance measuring method to prevent overfitting of embeddings in the consistent representation space. Extensive experiments conducted on five public real-world datasets demonstrate the effectiveness and efficiency of the proposed method. The code is available at: https://github.com/RUCAIBox/CORE.