Causal Recommendation via Machine Unlearning with a Few Unbiased Data

Meng Li, Haochen Sui

Keywords: Recommendation system, Machine Unlearning, error-maximizing pseudo-labels

TL;DR: we are the first work to address selection bias in recommender systems from a machine unlearning perspective.

Abstract: Recommender systems (RS) are increasingly important in so- cial media, entertainment, and e-commerce in the information explosion era. However, the collected data contains many bi- ases such as selection bias, as users are free to choose items to rate, making the collected data not representative of the target population. Recently, many methods such as relabeling-based and reweighting-based have been proposed to mitigate the selection bias. However, the effectiveness of these methods relies on strong assumptions, which are difficult to satisfy in real-world scenarios, leading to sub-optimal debiasing perfor- mance. In this paper, we propose a debiasing method from the machine unlearning perspective. Specifically, we first pro- pose a user unlearning rate network to determine which user needs to be unlearned. Then we generate the error-maximizing pseudo-labels for each user and fusion such pseudo-labels and the observed labels based on the learned user unlearning rate to mitigate the selection bias. In addition, we further propose an unlearning to debias training algorithm to achieve unbiased learning of the prediction model. Finally, we conduct exten- sive experiments on three real-world datasets to validate the effectiveness of our method.

Submission Number: 22