Invariant Collaborative Filtering to Popularity Distribution Shift

TL;DR

This paper introduces Invariant Collaborative Filtering (InvCF), a novel framework that learns disentangled, invariant representations to address popularity distribution shifts in recommendation systems, improving generalization without prior distribution knowledge.

Contribution

InvCF is the first method to learn popularity-invariant user preferences, effectively disentangling preference and popularity features without assuming prior distribution knowledge.

Findings

Outperforms state-of-the-art baselines in popularity generalization

Demonstrates robustness across multiple datasets and evaluation settings

Visualizations confirm effective disentangled representation learning

Abstract

Collaborative Filtering (CF) models, despite their great success, suffer from severe performance drops due to popularity distribution shifts, where these changes are ubiquitous and inevitable in real-world scenarios. Unfortunately, most leading popularity debiasing strategies, rather than tackling the vulnerability of CF models to varying popularity distributions, require prior knowledge of the test distribution to identify the degree of bias and further learn the popularity-entangled representations to mitigate the bias. Consequently, these models result in significant performance benefits in the target test set, while dramatically deviating the recommendation from users' true interests without knowing the popularity distribution in advance. In this work, we propose a novel learning framework, Invariant Collaborative Filtering (InvCF), to discover disentangled representations that faithfully reveal the latent preference and popularity semantics without making any assumption about the popularity distribution. At its core is the distillation of unbiased preference representations (i.e., user preference on item property), which are invariant to the change of popularity semantics, while filtering out the popularity feature that is unstable or outdated. Extensive experiments on five benchmark datasets and four evaluation settings (i.e., synthetic long-tail, unbiased, temporal split, and out-of-distribution evaluations) demonstrate that InvCF outperforms the state-of-the-art baselines in terms of popularity generalization ability on real recommendations. Visualization studies shed light on the advantages of InvCF for disentangled representation learning. Our codes are available at https://github.com/anzhang314/InvCF.