COLA: Improving Conversational Recommender Systems by Collaborative Augmentation

TL;DR

This paper introduces COLA, a collaborative augmentation method that enhances conversational recommender systems by leveraging user-item interaction graphs and similar conversations to improve item representations and user preference modeling.

Contribution

The paper proposes a novel collaborative augmentation approach that incorporates item popularity and similar conversations to improve CRS performance, addressing limitations of prior methods.

Findings

Significant improvement in recommendation accuracy on benchmark datasets.

Effective augmentation of item and user representations through collaborative filtering.

Demonstrated robustness across different conversational scenarios.

Abstract

Conversational recommender systems (CRS) aim to employ natural language conversations to suggest suitable products to users. Understanding user preferences for prospective items and learning efficient item representations are crucial for CRS. Despite various attempts, earlier studies mostly learned item representations based on individual conversations, ignoring item popularity embodied among all others. Besides, they still need support in efficiently capturing user preferences since the information reflected in a single conversation is limited. Inspired by collaborative filtering, we propose a collaborative augmentation (COLA) method to simultaneously improve both item representation learning and user preference modeling to address these issues. We construct an interactive user-item graph from all conversations, which augments item representations with user-aware information, i.e., item popularity. To improve user preference modeling, we retrieve similar conversations from the training corpus, where the involved items and attributes that reflect the user's potential interests are used to augment the user representation through gate control. Extensive experiments on two benchmark datasets demonstrate the effectiveness of our method. Our code and data are available at https://github.com/DongdingLin/COLA.