将用户兴趣建模为潜在空间中的随机过程，缓解推荐系统偏差问题。
Session-based Recommender Systems: User Interest as a Stochastic Process in the Latent Space
- 把用户兴趣看作潜在空间的随机过程，统一建模不确定性。
- 在Diginetica和YooChoose数据集上显著降低热门商品偏见。
- 无需修改模型即可适配，适合做公平性优化的研究者使用。
本文联合解决会话推荐系统中的数据不确定性、流行度偏见和曝光偏见问题。研究了这些偏见在物品嵌入和推荐结果中的表现。提出将用户兴趣视为潜在空间中的随机过程，并提供一种与模型无关的实现方式。该方法包含三个核心组件：通过嵌入均匀性正则化去偏物品嵌入，基于会话前缀建模密集用户兴趣，以及在数据中引入虚假目标以模拟更长曝光。在两个主流基准数据集Diginetica和YooChoose 1/64，以及多个不同热门商品比例的YooChoose变体上进行了计算实验。结果表明，所提方法能有效缓解上述挑战。
原文摘要 · Abstract (English)
This paper jointly addresses the problem of data uncertainty, popularity bias, and exposure bias in session-based recommender systems. We study the symptoms of this bias both in item embeddings and in recommendations. We propose treating user interest as a stochastic process in the latent space and providing a model-agnostic implementation of this mathematical concept. The proposed stochastic component consists of elements: debiasing item embeddings with regularization for embedding uniformity, modeling dense user interest from session prefixes, and introducing fake targets in the data to simulate extended exposure. We conducted computational experiments on two popular benchmark datasets, Diginetica and YooChoose 1/64, as well as several modifications of the YooChoose dataset with different ratios of popular items. The results show that the proposed approach allows us to mitigate the challenges mentioned.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。