Implicit feedback has been widely used to build commercial recommender systems. Because observed feedback represents users' click logs, there is a semantic gap between true relevance and observed feedback. More importantly, observed feedback is usually biased towards popular items, thereby overestimating the actual relevance of popular items. Although existing studies have developed unbiased learning methods using inverse propensity weighting (IPW) or causal reasoning, they solely focus on eliminating the popularity bias of items. In this paper, we propose a novel unbiased recommender learning model, namely BIlateral SElf-unbiased Recommender (BISER), to eliminate the exposure bias of items caused by recommender models. Specifically, BISER consists of two key components: (i) self-inverse propensity weighting (SIPW) to gradually mitigate the bias of items without incurring high computational costs; and (ii) bilateral unbiased learning (BU) to bridge the gap between two complementary models in model predictions, i.e., user- and item-based autoencoders, alleviating the high variance of SIPW. Extensive experiments show that BISER consistently outperforms state-of-the-art unbiased recommender models over several datasets, including Coat, Yahoo! R3, MovieLens, and CiteULike.
翻译:由于观测到的反馈代表了用户点击记录,因此在真实相关性和观察到的反馈之间存在语义上的差距。更重要的是,观测到的反馈通常偏向流行项目,从而高估了流行项目的实际相关性。虽然现有研究开发了不带偏见的学习方法,使用了反向偏向权重或因果推理,但仅侧重于消除项目的受欢迎偏向性。在本文件中,我们提出了一个新的不偏向性建议学习模式,即BIMain Self-unbised Agrouper (BISER),以消除推荐者模型导致的物品暴露偏差。具体地说,BISier由两个关键组成部分组成:(一) 自我反偏向性偏重(SIPW) 以逐步减少项目的偏向性,而不会引起高昂的计算成本;(二) 双边无偏见学习(BUB) 以弥合模型预测中两个互补模式之间的差距,即用户和基于项目的自动解析器,以缓解SIPW的高度差异。广泛的实验显示BISERS-ARESARES-AMAL3号、Allestal-CLANS-CANS-CANDLANS-CANS-RAND-SMA-SMA-R-IAR3号、C-IAR-IAR-IAR-IAR3号、C-IAR-IAR-SAR-SAR-IAR3号、C-IAR-SAR-LAS-C-IAR3号模型等若干数据。