Cao Tianwei, Xu Qianqian, Yang Zhiyong, Huang Qingming
IEEE Trans Pattern Anal Mach Intell. 2024 Feb;46(2):957-974. doi: 10.1109/TPAMI.2023.3327411. Epub 2024 Jan 8.
To improve user experience, recommender systems have been widely used on many online platforms. In these systems, recommendation models are typically learned from positive/negative feedback that are collected automatically. Notably, recommender systems are a little different from general supervised learning tasks. In recommender systems, there are some factors (e.g., previous recommendation models or operation strategies of a online platform) that determine which items can be exposed to each individual user. Normally, the previous exposure results are not only relevant to the instances' features (i.e., user or item), but also affect their feedback ratings, thus leading to confounding bias in the recommendation models. To mitigate this bias, researchers have already provided a variety of strategies. However, there are still two issues that are underappreciated: 1) previous debiased RS approaches cannot effectively capture recommendation-specific, exposure-specific and their common knowledge simultaneously; 2) the true exposure results of the user-item pairs are partially inaccessible, so there would be some noises if we use their observability to approximate it as existing approaches. Motivated by this, we develop a novel debiasing recommendation approach. More specifically, we first propose a mutual information-based counterfactual learning framework based on the causal relationship among the instance features, exposure status, and ratings. This framework can 1) capture recommendation-specific, exposure-specific and their common knowledge by explicitly modeling the relationship among the causal factors, and 2) achieve robustness towards partially inaccessible exposure results by a pairwise learning strategy. Under such a framework, we implement an optimizable loss function with theoretical analysis. By minimizing this loss, we expect to obtain an unbiased recommendation model that reflects the users' real interests. Meanwhile, we also prove that our loss function has robustness towards the partial inaccessibility of the exposure status. Finally, extensive experiments on public datasets manifest the superiority of our proposed method in boosting the recommendation performance.
为了提升用户体验，推荐系统已在众多在线平台中广泛应用。在这些系统里，推荐模型通常是从自动收集的正/负反馈中学习得到。值得注意的是，推荐系统与一般的监督学习任务略有不同。在推荐系统中，存在一些因素（例如，先前的推荐模型或在线平台的运营策略）决定哪些物品能够展示给每个用户。通常情况下，先前的展示结果不仅与实例的特征（即用户或物品）相关，还会影响它们的反馈评分，从而导致推荐模型中出现混杂偏差。为了减轻这种偏差，研究人员已经提出了多种策略。然而，仍有两个未得到充分重视的问题：1）先前的去偏推荐系统方法无法同时有效地捕捉特定于推荐、特定于曝光及其共同知识；2）用户-物品对的真实曝光结果部分不可获取，因此如果我们像现有方法那样使用其可观测性来近似它，将会产生一些噪声。受此启发，我们开发了一种新颖的去偏推荐方法。更具体地说，我们首先基于实例特征、曝光状态和评分之间的因果关系，提出了一种基于互信息的反事实学习框架。该框架能够：1）通过明确建模因果因素之间的关系，捕捉特定于推荐、特定于曝光及其共同知识；2）通过成对学习策略实现对部分不可获取的曝光结果的鲁棒性。在这样的框架下，我们通过理论分析实现了一个可优化的损失函数。通过最小化这个损失，我们期望获得一个反映用户真实兴趣的无偏推荐模型。同时，我们还证明了我们的损失函数对于曝光状态的部分不可获取具有鲁棒性。最后，在公共数据集上进行的大量实验表明了我们所提出方法在提升推荐性能方面的优越性。
