CIRS:通过反事实交互式推荐系统打破过滤气泡
CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender System
AI总结:
本文提出融合因果推断与离线强化学习的交互式推荐系统 CIRS,通过因果用户模型刻画过度曝光效应并优化长期满意度,同时构建 KuaiEnv 验证其能有效打破过滤气泡。
摘要:
尽管个性化提高了推荐系统的效用,但它也带来了过滤气泡问题。例如,如果系统持续曝光并推荐用户感兴趣的物品,可能会让用户感到无聊并降低满意度。现有工作研究静态推荐中的过滤气泡,在这种场景下过度曝光的影响很难被捕捉。相比之下,我们认为在交互式推荐中研究该问题并优化长期用户满意度更有意义。然而,由于成本高昂,在线训练模型并不现实。因此,我们必须利用离线训练数据,并分离对用户满意度的因果影响。为实现这一目标,我们提出了一种反事实交互式推荐系统(CIRS),利用因果推断增强离线强化学习(offline RL)。其基本思想是首先在历史数据上学习因果用户模型,以捕捉物品对用户满意度的过度曝光影响;随后使用学到的因果用户模型辅助 RL 策略的规划。为了进行离线评估,我们基于真实世界的完全观测用户评分数据集,创新性地构建了一个真实的 RL 环境(KuaiEnv)。实验表明,CIRS 在打破过滤气泡以及在交互式推荐中取得长期成功方面具有有效性。CIRS 的实现可通过 https://github.com/chongminggao/CIRS-codes 获取。
英文摘要:
While personalization increases the utility of recommender systems, it also brings the issue of filter bubbles. E.g., if the system keeps exposing and recommending the items that the user is interested in, it may also make the user feel bored and less satisfied. Existing work studies filter bubbles in static recommendation, where the effect of overexposure is hard to capture. In contrast, we believe it is more meaningful to study the issue in interactive recommendation and optimize long-term user satisfaction. Nevertheless, it is unrealistic to train the model online due to the high cost. As such, we have to leverage offline training data and disentangle the causal effect on user satisfaction. To achieve this goal, we propose a counterfactual interactive recommender system (CIRS) that augments offline reinforcement learning (offline RL) with causal inference. The basic idea is to first learn a causal user model on historical data to capture the overexposure effect of items on user satisfaction. It then uses the learned causal user model to help the planning of the RL policy. To conduct evaluation offline, we innovatively create an authentic RL environment (KuaiEnv) based on a real-world fully observed user rating dataset. The experiments show the effectiveness of CIRS in bursting filter bubbles and achieving long-term success in interactive recommendation. The implementation of CIRS is available via https://github.com/chongminggao/CIRS-codes.
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。