Learning from All Sides: Diversified Positive Augmentation via Self-distillation in Recommendation

TL;DR

This paper introduces DivSPA, a self-distillation based method that enhances recommendation systems by providing accurate and diverse positive item augmentations, addressing data sparsity effectively.

Contribution

The paper proposes a novel, model-agnostic Diversified self-distillation guided positive augmentation method that improves both accuracy and diversity in recommendation systems.

Findings

DivSPA improves recommendation accuracy and diversity in offline tests.

DivSPA is simple, effective, and adaptable to various models.

DivSPA has been successfully deployed in real-world recommender systems.

Abstract

Personalized recommendation relies on user historical behaviors to provide user-interested items, and thus seriously struggles with the data sparsity issue. A powerful positive item augmentation is beneficial to address the sparsity issue, while few works could jointly consider both the accuracy and diversity of these augmented training labels. In this work, we propose a novel model-agnostic Diversified self-distillation guided positive augmentation (DivSPA) for accurate and diverse positive item augmentations. Specifically, DivSPA first conducts three types of retrieval strategies to collect high-quality and diverse positive item candidates according to users' overall interests, short-term intentions, and similar users. Next, a self-distillation module is conducted to double-check and rerank these candidates as the final positive augmentations. Extensive offline and online evaluations verify the effectiveness of our proposed DivSPA on both accuracy and diversity. DivSPA is simple and effective, which could be conveniently adapted to other base models and systems. Currently, DivSPA has been deployed on multiple widely-used real-world recommender systems.