Are Big Recommendation Models Fair to Cold Users?

TL;DR

This paper investigates fairness issues in large recommendation models, showing they favor heavy users over cold users, and proposes a self-distillation method called BigFair to improve fairness without sacrificing overall performance.

Contribution

The paper introduces BigFair, a novel self-distillation approach that enhances fairness for cold users in big recommendation models, addressing a key bias in current systems.

Findings

BigFair improves fairness for cold users.

The method maintains overall recommendation performance.

Experiments on two datasets validate effectiveness.

Abstract

Big models are widely used by online recommender systems to boost recommendation performance. They are usually learned on historical user behavior data to infer user interest and predict future user behaviors (e.g., clicks). In fact, the behaviors of heavy users with more historical behaviors can usually provide richer clues than cold users in interest modeling and future behavior prediction. Big models may favor heavy users by learning more from their behavior patterns and bring unfairness to cold users. In this paper, we study whether big recommendation models are fair to cold users. We empirically demonstrate that optimizing the overall performance of big recommendation models may lead to unfairness to cold users in terms of performance degradation. To solve this problem, we propose a BigFair method based on self-distillation, which uses the model predictions on original user data as a teacher to regularize predictions on augmented data with randomly dropped user behaviors, which can encourage the model to fairly capture interest distributions of heavy and cold users. Experiments on two datasets show that BigFair can effectively improve the performance fairness of big recommendation models on cold users without harming the performance on heavy users.