HyCoRec: Hypergraph-Enhanced Multi-Preference Learning for Alleviating Matthew Effect in Conversational Recommendation
2026-07-20 • Information Retrieval
Information RetrievalArtificial IntelligenceHuman-Computer Interaction
AI summaryⓘ
The authors address a problem in recommendation systems called the Matthew effect, where popular items keep getting more attention while less popular ones are ignored. They focus on conversational recommendation systems, where this problem worsens over time as a user interacts more with the system. To fix this, they created HyCoRec, a method that looks at many different preferences like items, entities, words, reviews, and knowledge to better recommend and chat with users. Their tests show HyCoRec improves recommendations and reduces the Matthew effect compared to previous methods.
Recommender SystemsMatthew effectConversational recommendationHypergraphMulti-preference learningItem recommendationUser interactionResponse generationKnowledge-aspect preference
Authors
Yongsen Zheng, Ruilin Xu, Ziliang Chen, Guohua Wang, Mingjie Qian, Jinghui Qin, Liang Lin
Abstract
The Matthew effect is a notorious issue in Recommender Systems (RSs), \emph{i.e.}, the rich get richer and the poor get poorer, wherein popular items are overexposed while less popular ones are regularly ignored. Most methods examine Matthew effect in static or nearly-static recommendation scenarios. However, the Matthew effect will be increasingly amplified when the user interacts with the system over time. To address these issues, we propose a novel paradigm, Hypergraph-Enhanced Multi-Preference Learning for Alleviating Matthew Effect in Conversational Recommendation (HyCoRec), which aims to alleviate the Matthew effect in conversational recommendation. Concretely, HyCoRec devotes to alleviate the Matthew effect by learning multi-aspect preferences, \emph{i.e.}, item-, entity-, word-, review-, and knowledge-aspect preferences, to effectively generate responses in the conversational task and accurately predict items in the recommendation task when the user chats with the system over time. Extensive experiments conducted on two benchmarks validate that HyCoRec achieves new state-of-the-art performance and the superior of alleviating Matthew effect. Our code is available at https://github.com/zysensmile/HyCoRec.