arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.01616cs.IRcs.LGstat.ML
收藏

基于因果推理的推荐系统中反馈环的破环

Breaking Feedback Loops in Recommender Systems with Causal Inference

University of California Berkeley(加州大学伯克利分校);University of Michigan(密歇根大学)

Karl Krauth, Yixin Wang, Michael I. Jordan

摘要:

推荐系统在塑造现代网络生态系统中发挥着关键作用。这些系统在(1)做出推荐(2)收集用户对这些推荐的响应以及(3)基于该反馈重新训练推荐算法之间交替。在此过程中,推荐系统会影响随后用于更新的用户行为数据,从而创建一个反馈循环。最近的工作表明,反馈循环可能会损害推荐质量和同质化的用户行为,提高道德和性能的关注时,部署推荐系统。为了解决这些问题,我们提出了反馈循环因果调整(CAFL),这是一种使用因果推理可证明地打破反馈循环的算法,可以应用于任何优化训练损失的推荐算法。我们的主要观察是,一个推荐系统不会遭受反馈回路,如果它的原因因果量,即干预分布的建议用户评级。此外,我们可以通过调整推荐系统对用户偏好的预测,从观察数据中计算出这种干预分布。使用模拟环境中,我们证明了CAFL提高推荐质量相比,以前的校正方法。

英文摘要:

Recommender systems play a key role in shaping modern web ecosystems. These systems alternate between (1) making recommendations (2) collecting user responses to these recommendations, and (3) retraining the recommendation algorithm based on this feedback. During this process the recommender system influences the user behavioral data that is subsequently used to update it, thus creating a feedback loop. Recent work has shown that feedback loops may compromise recommendation quality and homogenize user behavior, raising ethical and performance concerns when deploying recommender systems. To address these issues, we propose the Causal Adjustment for Feedback Loops (CAFL), an algorithm that provably breaks feedback loops using causal inference and can be applied to any recommendation algorithm that optimizes a training loss. Our main observation is that a recommender system does not suffer from feedback loops if it reasons about causal quantities, namely the intervention distributions of recommendations on user ratings. Moreover, we can calculate this intervention distribution from observational data by adjusting for the recommender system's predictions of user preferences. Using simulated environments, we demonstrate that CAFL improves recommendation quality when compared to prior correction methods.

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。

↑