arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.04589cs.IRcs.AI
收藏

面向多行为推荐公平性的因果干预方法

Causal Intervention for Fairness in Multi-behavior Recommendation

Beihang University(北京航空航天大学);National University of Singapore(新加坡国立大学);University of Science and Technology of China(中国科学技术大学)

Xi Wang, Wenjie Wang, Fuli Feng, Wenge Rong, Chuantao Yin, Zhang Xiong

AI总结:

针对多行为推荐中流行度偏差导致的两类不公平问题,提出基于后门调整的因果框架,通过阻断混杂因素路径、平衡流行度与质量影响,在不损失准确率的前提下提升推荐公平性。

摘要:

推荐系统通常从各类用户行为中学习用户兴趣,包括点击行为与点击后行为(如点赞、收藏)。但这些行为不可避免地存在流行度偏差,进而引发两类不公平问题:1)质量相近的物品中,更流行的物品获得更多曝光;2)更严重的是,流行度更低的热门物品反而可能获得更多曝光。现有缓解流行度偏差的研究多是盲目消除偏差,且通常忽略了物品质量的影响。我们认为,不同用户行为之间的关系(如转化率)实际上能够反映物品质量。因此,为解决上述不公平问题,我们提出通过结合多种用户行为来缓解流行度偏差。\n在本研究中,我们探究了多行为推荐中交互生成过程背后的因果关系。具体而言,我们发现:1)物品流行度是曝光物品与用户点击后交互之间的混杂因素,导致了第一类不公平;2)部分隐藏混杂因素(如物品创作者的声誉)会同时影响物品的流行度与质量,进而引发第二类不公平。为缓解这些混杂问题,我们提出了一个用于估计因果效应的因果框架,该框架利用后门调整来阻断由混杂因素引发的后门路径。在推理阶段,我们移除流行度的负面影响,同时利用质量的正向作用进行推荐。在两个真实世界数据集上的实验验证了所提框架的有效性,其在不牺牲推荐准确率的前提下提升了公平性。

英文摘要:

Recommender systems usually learn user interests from various user behaviors, including clicks and post-click behaviors (e.g., like and favorite). However, these behaviors inevitably exhibit popularity bias, leading to some unfairness issues: 1) for items with similar quality, more popular ones get more exposure; and 2) even worse the popular items with lower popularity might receive more exposure. Existing work on mitigating popularity bias blindly eliminates the bias and usually ignores the effect of item quality. We argue that the relationships between different user behaviors (e.g., conversion rate) actually reflect the item quality. Therefore, to handle the unfairness issues, we propose to mitigate the popularity bias by considering multiple user behaviors. In this work, we examine causal relationships behind the interaction generation procedure in multi-behavior recommendation. Specifically, we find that: 1) item popularity is a confounder between the exposed items and users' post-click interactions, leading to the first unfairness; and 2) some hidden confounders (e.g., the reputation of item producers) affect both item popularity and quality, resulting in the second unfairness. To alleviate these confounding issues, we propose a causal framework to estimate the causal effect, which leverages backdoor adjustment to block the backdoor paths caused by the confounders. In the inference stage, we remove the negative effect of popularity and utilize the good effect of quality for recommendation. Experiments on two real-world datasets validate the effectiveness of our proposed framework, which enhances fairness without sacrificing recommendation accuracy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑