Automatic Self-supervised Learning for Social Recommendations

TL;DR

This paper introduces AusRec, a self-supervised learning framework that adaptively balances multiple auxiliary tasks to improve social recommendation systems, demonstrated by superior performance on real-world datasets.

Contribution

AusRec automatically learns the importance of auxiliary tasks using meta-learning, reducing reliance on domain-specific task design in social recommendation models.

Findings

AusRec outperforms state-of-the-art baselines on multiple datasets.

The adaptive weighting mechanism improves recommendation accuracy.

The framework is robust across different social recommendation scenarios.

Abstract

In recent years, researchers have leveraged social relations to enhance recommendation performance. However, most existing social recommendation methods require carefully designed auxiliary social tasks tailored to specific scenarios, which depend heavily on domain knowledge and expertise. To address this limitation, we propose Automatic Self-supervised Learning for Social Recommendations (AusRec), which integrates multiple self-supervised auxiliary tasks with an automatic weighting mechanism to adaptively balance their contributions through a meta-learning optimization framework. This design enables the model to automatically learn the optimal importance of each auxiliary task, thereby enhancing representation learning in social recommendations. Extensive experiments on several real-world datasets demonstrate that AusRec consistently outperforms state-of-the-art baselines, validating its effectiveness and robustness across different recommendation scenarios.