The paper proposes a novel framework called Knowledge-Aware Multi-Intent Contrastive Learning (KAMCL) for multi-behavior recommendation. The key highlights are:
KAMCL uses relationships in the knowledge graph to construct user intents, aiming to mine the connections between users' multi-behaviors from the perspective of intents to achieve more accurate recommendations.
KAMCL is equipped with two contrastive learning schemes - relation-aware item contrastive learning and behavior-aware user contrastive learning. These schemes help alleviate the data scarcity problem and further enhance user and item representations.
The relation-aware knowledge graph aggregation module extracts semantic information about items from different perspectives by partitioning the knowledge graph based on relations.
The intent generation module leverages the relational information in the knowledge graph to capture user intent information across different behaviors.
The intent-based multi-behavior interaction module explores the connections between behaviors from the perspective of user intent.
Extensive experiments on three real-world datasets demonstrate the superiority of KAMCL over state-of-the-art multi-behavior recommendation methods.
Vers une autre langue
à partir du contenu source
arxiv.org
Questions plus approfondies