Debiasing the Cloze Task in Sequential Recommendation with Bidirectional Transformers
Debiasing the Cloze Task in Sequential Recommendation with Bidirectional Transformers
复制标题
DOI：
10.1145/3534678.3539430
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
Khalil Damak;Sami Khenissi;O. Nasraoui
中科院分区：
文献类型：
--
作者：
Khalil Damak;Sami Khenissi;O. Nasraoui
双向Transformer架构是最先进的顺序推荐模型，它使用基于完形填空任务的双向表示能力，也称为“完形填空”。屏蔽语言建模。后者旨在预测序列中随机掩蔽的项目。因为他们假设真正的互动项目是最相关的，暴露偏差的结果，其中具有低暴露倾向的非互动项目被认为是不相关的。在推荐中减轻暴露偏差的最常见方法是逆倾向评分（IPS），其包括在损失函数中按暴露倾向成比例地降低相互作用的预测的权重，从而产生理论上无偏的学习。在这项工作中，我们认为，并证明IPS不扩展到顺序推荐，因为它没有考虑到问题的时间性质。然后，我们提出了一种新的倾向评分机制，理论上可以消除顺序推荐中完形填空任务的偏见。最后，我们实证证明了我们提出的方法的去偏置能力和它的鲁棒性的曝光偏差的严重程度。
Bidirectional Transformer architectures are state-of-the-art sequential recommendation models that use a bi-directional representation capacity based on the Cloze task, a.k.a. Masked Language Modeling. The latter aims to predict randomly masked items within the sequence. Because they assume that the true interacted item is the most relevant one, an exposure bias results, where non-interacted items with low exposure propensities are assumed to be irrelevant. The most common approach to mitigating exposure bias in recommendation has been Inverse Propensity Scoring (IPS), which consists of down-weighting the interacted predictions in the loss function in proportion to their propensities of exposure, yielding a theoretically unbiased learning. In this work, we argue and prove that IPS does not extend to sequential recommendation because it fails to account for the temporal nature of the problem. We then propose a novel propensity scoring mechanism, which can theoretically debias the Cloze task in sequential recommendation. Finally we empirically demonstrate the debiasing capabilities of our proposed approach and its robustness to the severity of exposure bias.