This work studies the problem of learning unbiased algorithms from biased feedback for recommender systems. We address this problem from both theoretical and algorithmic perspectives. Recent works in unbiased learning have advanced the state-of-the-art with various techniques such as meta-learning, knowledge distillation, and information bottleneck. Despite their empirical successes, most of them lack theoretical guarantee, forming non-negligible gaps between the theories and recent algorithms. To this end, we first view the unbiased recommendation problem from a distribution shift perspective. We theoretically analyze the generalization bounds of unbiased learning and suggest their close relations with recent unbiased learning objectives. Based on the theoretical analysis, we further propose a principled framework, Adversarial Self-Training (AST), for unbiased recommendation. Empirical evaluation on real-world and semi-synthetic datasets demonstrate the effectiveness of the proposed AST.
翻译:这项工作研究从对建议者系统的有偏见的反馈中学习不带偏见的算法的问题。我们从理论和算法的角度来处理这个问题。最近进行的不带偏见的学习工作以诸如元学习、知识蒸馏和信息瓶颈等各种技术推进了最先进的技术。尽管它们取得了成功,但大多数缺乏理论保证,在理论和最近算法之间形成了不可忽略的差距。为此目的,我们首先从分配转移的角度来看待不带偏见的建议问题。我们从理论上分析不偏倚学习的概括性界限,并建议它们与最近的不偏倚学习目标的密切关系。我们根据理论分析,进一步提出了一个原则框架,即自学自学(AST),以便提出不带偏见的建议。对现实世界和半合成数据集的实证评估显示了拟议的AST的有效性。