Language-Enhanced Session-Based Recommendation with Decoupled Contrastive Learning

TL;DR

This paper introduces a multimodal session-based recommendation method that combines textual content and item IDs, utilizing decoupled contrastive learning to improve user preference modeling and address cold-start issues.

Contribution

It proposes a novel hybrid approach integrating language models and contrastive learning with dual-queue mechanisms for better item representation and recommendation accuracy.

Findings

Achieved 5th place in KDD CUP 2023 Task 1

Enhanced item representation through language models

Improved contrastive learning with dual-queue strategy

Abstract

Session-based recommendation techniques aim to capture dynamic user behavior by analyzing past interactions. However, existing methods heavily rely on historical item ID sequences to extract user preferences, leading to challenges such as popular bias and cold-start problems. In this paper, we propose a hybrid multimodal approach for session-based recommendation to address these challenges. Our approach combines different modalities, including textual content and item IDs, leveraging the complementary nature of these modalities using CatBoost. To learn universal item representations, we design a language representation-based item retrieval architecture that extracts features from the textual content utilizing pre-trained language models. Furthermore, we introduce a novel Decoupled Contrastive Learning method to enhance the effectiveness of the language representation. This technique decouples the sequence representation and item representation space, facilitating bidirectional alignment through dual-queue contrastive learning. Simultaneously, the momentum queue provides a large number of negative samples, effectively enhancing the effectiveness of contrastive learning. Our approach yielded competitive results, securing a 5th place ranking in KDD CUP 2023 Task 1. We have released the source code and pre-trained models associated with this work.