Mitigating Spurious Correlations for Self-supervised Recommendation  

作　　者：Xin-Yu Lin Yi-Yan Xu Wen-Jie Wang Yang Zhang Fu-Li Feng 

机构地区：[1]National University of Singapore,Queenstown 119077,Singapore [2]University of Science and Technology of China,Hefei 230026,China

出　　处：《Machine Intelligence Research》2023年第2期263-275,共13页机器智能研究（英文版）

摘　　要：Recent years have witnessed the great success of self-supervised learning(SSL)in recommendation systems.However,SSL recommender models are likely to suffer from spurious correlations,leading to poor generalization.To mitigate spurious correlations,existing work usually pursues ID-based SSL recommendation or utilizes feature engineering to identify spurious features.Nevertheless,ID-based SSL approaches sacrifice the positive impact of invariant features,while feature engineering methods require high-cost human labeling.To address the problems,we aim to automatically mitigate the effect of spurious correlations.This objective requires to 1)automatically mask spurious features without supervision,and 2)block the negative effect transmission from spurious features to other features during SSL.To handle the two challenges,we propose an invariant feature learning framework,which first divides user-item interactions into multiple environments with distribution shifts and then learns a feature mask mechanism to capture invariant features across environments.Based on the mask mechanism,we can remove the spurious features for robust predictions and block the negative effect transmission via mask-guided feature augmentation.Extensive experiments on two datasets demonstrate the effectiveness of the proposed framework in mitigating spurious correlations and improving the generalization abilities of SSL models.

关 键 词：Self-supervised recommendation spurious correlations spurious features invariant feature learning contrastive learning 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.3[自动化与计算机技术—控制科学与工程]