一句话：提出MV-HAN多视图混合注意力模型，通过参数共享与统一特征空间提升大规模推荐内容检索，尤其改善稀疏类型。
工业推荐系统常利用多源数据提升推荐质量，但不同数据源之间的信息共享仍具挑战。本文提出一种用于推荐系统匹配阶段内容检索的多视图混合注意力网络模型（MV-HAN）。该模型支持多种输入特征间的高阶交互，并通过精心设计的参数共享策略在不同类型之间迁移知识，从而显著提升稀疏类型的检索效果。MV-HAN继承双塔模型在线服务效率优势，将不同类型用户与内容映射到同一特征空间，借助近似最近邻算法实现快速检索。作者在多个工业数据集上进行离线实验，表明MV-HAN在内容检索任务上显著优于基线；模型已部署于真实匹配系统，在线A/B测试显示其能显著提升推荐质量。
Industrial recommender systems usually employ multi-source data to improve the recommendation quality, while effectively sharing information between different data sources remain a challenge. In this paper, we introduce a novel Multi-View Approach with Hybrid Attentive Networks (MV-HAN) for contents retrieval at the matching stage of recommender systems. The proposed model enables high-order feature interaction from various input features while effectively transferring knowledge between different types. By employing a well-placed parameters sharing strategy, the MV-HAN substantially improves the retrieval performance in sparse types. The designed MV-HAN inherits the efficiency advantages in the online service from the two-tower model, by mapping users and contents of different types into the same features space. This enables fast retrieval of similar contents with an approximate nearest neighbor algorithm. We conduct offline experiments on several industrial datasets, demonstrating that the proposed MV-HAN significantly outperforms baselines on the content retrieval tasks. Importantly, the MV-HAN is deployed in a real-world matching system. Online A/B test results show that the proposed method can significantly improve the quality of recommendations.
@inproceedings{paperbot7160,
title = {MV-HAN: A Hybrid Attentive Networks based Multi-View Learning Model for Large-scale Contents Recommendation},
author = {Ge Fan and Chaoyun Zhang and Kai Wang and Junyang Chen},
booktitle = {ASE},
year = {2022},
doi = {10.1145/3551349.3559496}
}