Search papers, labs, and topics across Lattice.
This paper introduces HiCore, a novel framework designed to combat the Matthew effect in Conversational Recommender Systems (CRS) by leveraging multi-hypergraph structures to capture diverse user interests. By utilizing item-, entity-, and word-oriented hypergraphs, the framework effectively addresses the dynamic feedback loop between users and the system, which exacerbates the issue of popular items overshadowing less popular ones. Experimental results across four datasets demonstrate that HiCore achieves state-of-the-art performance in mitigating the Matthew effect, highlighting its effectiveness in enhancing recommendation fairness and diversity.
HiCore's innovative use of multi-hypergraphs enables it to significantly reduce the bias towards popular items in conversational recommendations, achieving unprecedented fairness in user engagement.
The Matthew effect is a big challenge in Recommender Systems (RSs), where popular items tend to receive increasing attention, while less popular ones are often overlooked, perpetuating existing disparities. Although many existing methods attempt to mitigate Matthew effect in the static or quasi-static recommendation scenarios, such issue will be more pronounced as users engage with the system over time. To this end, we propose a novel framework, Multi-Hypergraph Boosted Multi-Interest Self-Supervised Learning for Conversational Recommendation (HiCore), aiming to address Matthew effect in the Conversational Recommender System (CRS) involving the dynamic user-system feedback loop. It devotes to learn multi-level user interests by building a set of hypergraphs (i.e., item-, entity-, word-oriented multiple-channel hypergraphs) to alleviate the Matthew effec. Extensive experiments on four CRS-based datasets showcase that HiCore attains a new state-of-the-art performance, underscoring its superiority in mitigating the Matthew effect effectively. Our code is available at https://github.com/zysensmile/HiCore.
