Mitigating Spurious Correlations for Self-supervised Recommendation

TL;DR

This paper introduces an invariant feature learning framework that automatically identifies and masks spurious features in self-supervised recommendation models, enhancing their robustness and generalization without requiring manual feature engineering.

Contribution

It proposes a novel automatic masking mechanism that captures invariant features across distribution-shifted environments, mitigating spurious correlations in SSL recommendation systems.

Findings

Significantly reduces the impact of spurious correlations.

Improves generalization performance on unseen data.

Outperforms existing methods in experimental evaluations.

Abstract

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. The code is available at https://github.com/Linxyhaha/IFL.