Invariant debiasing learning for recommendation via biased imputation

TL;DR

This paper introduces KDDebias, a lightweight knowledge distillation framework that improves unbiased recommendation by imputing variant user preferences into invariant preferences, outperforming existing methods with fewer parameters.

Contribution

It proposes a novel biased imputation approach within a knowledge distillation framework to enhance invariant debiasing in recommendation systems.

Findings

Achieves significant improvements on three public datasets.

Uses less than 50% of the parameters compared to SOTA models.

Demonstrates the effectiveness of biased imputation in debiasing.

Abstract

Previous debiasing studies utilize unbiased data to make supervision of model training. They suffer from the high trial risks and experimental costs to obtain unbiased data. Recent research attempts to use invariant learning to detach the invariant preference of users for unbiased recommendations in an unsupervised way. However, it faces the drawbacks of low model accuracy and unstable prediction performance due to the losing cooperation with variant preference. In this paper, we experimentally demonstrate that invariant learning causes information loss by directly discarding the variant information, which reduces the generalization ability and results in the degradation of model performance in unbiased recommendations. Based on this consideration, we propose a novel lightweight knowledge distillation framework (KDDebias) to automatically learn the unbiased preference of users from both invariant and variant information. Specifically, the variant information is imputed to the invariant user preference in the distance-aware knowledge distillation process. Extensive experiments on three public datasets, i.e., Yahoo!R3, Coat, and MIND, show that with the biased imputation from the variant preference of users, our proposed method achieves significant improvements with less than 50% learning parameters compared to the SOTA unsupervised debiasing model in recommender systems. Our code is publicly available at https://github.com/BAI-LAB/KD-Debias.