A Modular Adversarial Approach to Social Recommendation
A Modular Adversarial Approach to Social Recommendation
复制标题
DOI：
10.1145/3357384.3357898
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
A. Krishnan;Hari Cheruvu;Tao Cheng;H. Sundaram
中科院分区：
文献类型：
--
作者：
A. Krishnan;Hari Cheruvu;Tao Cheng;H. Sundaram
本文提出了一种将社会正则化纳入项目推荐的新框架。基于同质性和影响力的社会正规化似乎抓住了潜在的用户偏好。然而，有两个关键的挑战：首先，特定社会联系的重要性取决于背景，其次，一个基本的结果表明，我们无法从观察数据中分离出同质性和影响，以确定社会推断的效果。因此，我们认为归因问题本质上是对立的，我们检查两个相互竞争的假设——社会影响和潜在利益——来解释每个购买决定。我们有两个贡献。首先，我们提出了一个模块化的、对抗性的框架，它将推荐和社会表示模型的架构选择解耦，以实现社会正则化。其次，我们通过直观的上下文加权策略克服退化解，该策略支持表达性归因，以确保信息社会关联在规范化学习用户兴趣空间中发挥更大的作用。我们的结果表明，在多个公开可用的数据集上，与最先进的基线相比，有显著的收益（相对Recall@K为5-10%）。
This paper proposes a novel framework to incorporate social regularization for item recommendation. Social regularization grounded in ideas of homophily and influence appears to capture latent user preferences. However, there are two key challenges: first, the importance of a specific social link depends on the context and second, a fundamental result states that we cannot disentangle homophily and influence from observational data to determine the effect of social inference. Thus we view the attribution problem as inherently adversarial where we examine two competing hypothesis---social influence and latent interests---to explain each purchase decision. We make two contributions. First, we propose a modular, adversarial framework that decouples the architectural choices for the recommender and social representation models, for social regularization. Second, we overcome degenerate solutions through an intuitive contextual weighting strategy, that supports an expressive attribution, to ensure informative social associations play a larger role in regularizing the learned user interest space. Our results indicate significant gains (5-10% relative Recall@K) over state-of-the-art baselines across multiple publicly available datasets.