论文标题
通过因果推理的推荐系统中打破反馈循环
Breaking Feedback Loops in Recommender Systems with Causal Inference
论文作者
论文摘要
推荐系统在塑造现代网络生态系统中起关键作用。这些系统在（1）提出建议之间交替（2）收集用户对这些建议的响应，以及（3）基于此反馈来重述建议算法。在此过程中，推荐系统会影响随后用于更新它的用户行为数据，从而创建反馈循环。最近的工作表明，反馈循环可能会损害建议质量并使用户行为均匀，从而在部署推荐系统时引起道德和绩效问题。为了解决这些问题，我们提出了反馈循环（CAFL）的因果调整，该算法可证明使用因果推理打破反馈回路，并可以应用于优化培训损失的任何建议算法。我们的主要观察结果是，如果原因是因果量的原因，即推荐系统不会遭受反馈循环的影响，即对用户评级的建议分布。此外，我们可以通过调整推荐系统对用户偏好的预测来计算观察数据中的干预分布。使用模拟环境，我们证明CAFL与先前的校正方法相比提高了建议质量。
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.
