用对比学习提升小群体推荐中的共识建模能力
C$^3$: Capturing Consensus with Contrastive Learning in Group Recommendation
- 基于Transformer和对比学习，同时建模用户与群体表征
- 在四个数据集上显著优于现有方法，兼顾个体与群体性能
- 特别适合小规模群体（2~5人）的推荐场景
群体推荐旨在为用户群体提供个性化推荐，其核心挑战在于建模反映成员偏好的共识。尽管现有深度学习模型取得一定进展，但仍存在两大不足：(1) 小群体（2~5人）推荐系统中共识建模仍具挑战，而这类场景更贴近真实应用；(2) 多数模型虽提升整体群体性能，却难以平衡个体与群体表现。为此，本文提出一种名为C³的群体推荐方法，通过对比学习捕捉群体决策背后的共识。采用Transformer编码器联合学习用户与群体表征，并利用对比学习缓解高交互用户过拟合问题，从而获得更鲁棒的群体表示。在四个公开数据集上的实验表明，C³在用户和群体推荐任务中均显著优于现有最优基线。
原文摘要 · Abstract (English)
Group recommendation aims to recommend tailored items to groups of users, where the key challenge is modeling a consensus that reflects member preferences. Although several existing deep learning models have achieved performance improvements, they still fail to capture consensus in various aspects: (1) Capturing consensus in small-group (2~5 members) recommendation systems, which align more closely with real-world scenarios, remains a significant challenge; (2) Most existing models significantly enhance the overall group performance but struggle with balancing individual and group performance. To address these issues, we propose Capturing Consensus with Contrastive Learning in Group Recommendation (C$^3$), which focuses on exploring the consensus behind group decision-making. A Transformer encoder is used to learn both group and user representations, and contrastive learning mitigates overfitting for users with many interactions, yielding more robust group representations. Experiments on four public datasets demonstrate that C$^3$ significantly outperforms state-of-the-art baselines in both user and group recommendation tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。