Session-based Recommender Systems: User Interest as a Stochastic Process in the Latent Space
This addresses bias issues in session-based recommenders, which is an incremental improvement for recommendation systems.
The paper tackles data uncertainty, popularity bias, and exposure bias in session-based recommender systems by modeling user interest as a stochastic process in latent space, showing that the approach mitigates these challenges on benchmark datasets like Diginetica and YooChoose.
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.