面向偏差问题的推荐方法研究综述

Review of recommendation methods for problem of bias

推荐系统偏差的研究众多但零散,相关研究综述较少。因此,根据偏差产生的主体将偏差分为用户行为导致的偏差、物品展示导致的偏差和推荐算法导致的偏差,进而又细分为选择偏差、一致性偏差等九种具体的类别,并给出各个偏差的定义和造成原因;着重对解决偏差问题的相关性推荐方法和因果性推荐方法的研究进行整理,并根据所采用技术手段或者所处训练模型的前、中、后三个阶段进一步分类,分析不同类别研究之间的区别和优势;总结了在常用数据集上的偏差研究概况和新提出的偏差衡量指标;从不同的类别角度对面向偏差问题的推荐方法发展趋势进行分析和展望,希望为推荐系统中的后续的偏差研究提供一定的帮助。

Due to the numerous but scattered studies on the bias of recommendation systems and few relevant research reviews,according to the subject that causes the bias,this paper divided bias into the bias in user behavior,the bias in item display,and the bias in recommendation algorithm,and then subdivided it into nine specific categories,such as selection bias and conformity bias,and gave the definition and causes of each bias.This paper focused on sorting out the research on correlation recommendation methods and causal recommendation methods to solve the bias problem,and further classified them according to the technical means or the first,middle and last three stages of the training model,and analyzed the differences and strengths between different types of research.This paper summarized the bias studies on common datasets and new bias measures,forecasted the development trend of bias-oriented recommendation methods from different categories,hoping to provide some help for the follow-up bias research in recommender system.