用对比学习增强社交推荐，提升冷用户效果
Contrastive Learning Augmented Social Recommendations
- 双视角去噪：用低秩SVD和对比学习修复社交图
- 冷用户精度提升12.3%，整体推荐效果优于基线
- 适合做社交推荐、冷启动问题的研究与应用
推荐系统对现代内容平台至关重要，但传统基于行为的模型在冷用户（交互数据少）上表现不佳。为解决此问题，我们利用社交关系图增强行为模型的兴趣表示。然而，社交图存在关系噪声和跨域不一致问题。为此，提出双视角去噪策略：通过低秩SVD对用户-物品交互矩阵进行分解以获得去噪社交图，并使用对比学习对齐原始与重构社交图。为缓解社交与行为兴趣间的不一致，采用“互蒸馏”技术，将原始兴趣分解为对齐的社交/行为兴趣及各自特有兴趣，最大化双重信息价值。在多个主流工业数据集上的实验验证了方法的有效性，尤其在冷用户场景下表现显著，为未来研究提供了新思路。代码已开源：https://github.com/WANGLin0126/CLSRec。
原文摘要 · Abstract (English)
Recommender systems are essential for modern content platforms, yet traditional behavior-based models often struggle with cold users who have limited interaction data. Engaging these users is crucial for platform growth. To bridge this gap, we propose leveraging the social-relation graph to enrich interest representations from behavior-based models. However, extracting value from social graphs is challenging due to relation noise and cross-domain inconsistency. To address the noise propagation and obtain accurate social interest, we employ a dual-view denoising strategy, employing low-rank SVD to the user-item interaction matrix for a denoised social graph and contrastive learning to align the original and reconstructed social graphs. Addressing the interest inconsistency between social and behavioral interests, we adopt a "mutual distillation" technique to isolate the original interests into aligned social/behavior interests and social/behavior specific interests, maximizing the utility of both. Experimental results on widely adopted industry datasets verify the method's effectiveness, particularly for cold users, offering a fresh perspective for future research. The implementation can be accessed at https://github.com/WANGLin0126/CLSRec.
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。