解决多领域推荐中数据不均衡导致的模型偏移与过拟合问题。
A Soft-partitioned Semi-supervised Collaborative Transfer Learning Approach for Multi-Domain Recommendation
- 通过动态参数分配，缓解主导领域对模型的过度影响。
- 利用主导领域加权伪标签增强非主导领域数据，提升泛化能力。
- 适用于电商等多领域推荐场景，尤其适合数据稀疏的长尾领域。
在工业实践中，多领域推荐（MDR）至关重要。现有共享-专用架构虽能捕捉共性和特性，但在跨领域数据分布不均时面临两大挑战：(1) 过度主导：主导领域数据使模型性能偏向自身，忽略非主导领域；(2) 过拟合：非主导领域数据稀疏，导致专用参数过拟合。为此，我们提出软划分半监督协同迁移学习（SSCTL）方法。该方法通过生成动态参数缓解过度主导问题，将注意力转向非主导领域样本；同时引入来自主导领域实例的加权伪标签，以增强非主导领域数据表征。我们在真实线上和离线环境下进行充分实验，验证了所提方法的有效性。在线测试显示，各领域GMV提升0.54%至2.90%，点击率（CTR）提升0.22%至1.69%。
原文摘要 · Abstract (English)
In industrial practice, Multi-domain Recommendation (MDR) plays a crucial role. Shared-specific architectures are widely used in industrial solutions to capture shared and unique attributes via shared and specific parameters. However, with imbalanced data across different domains, these models face two key issues: (1) Overwhelming: Dominant domain data skews model performance, neglecting non-dominant domains. (2) Overfitting: Sparse data in non-dominant domains leads to overfitting in specific parameters. To tackle these challenges, we propose Soft-partitioned Semi-supervised Collaborative Transfer Learning (SSCTL) for multi-domain recommendation. SSCTL generates dynamic parameters to address the overwhelming issue, thus shifting focus towards samples from non-dominant domains. To combat overfitting, it leverages pseudo-labels with weights from dominant domain instances to enhance non-dominant domain data. We conduct comprehensive experiments, both online and offline, to validate the efficacy of our proposed method. Online tests yielded significant improvements across various domains, with increases in GMV ranging from 0.54% to 2.90% and enhancements in CTR ranging from 0.22% to 1.69%.
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。