Frequency-aware Adaptive Contrastive Learning for Sequential Recommendation

TL;DR

This paper introduces FACL, a frequency-aware contrastive learning framework that enhances sequential recommendation by addressing biases against low-frequency items, leading to improved accuracy and robustness in long-tail scenarios.

Contribution

FACL is the first to incorporate micro-level adaptive perturbation and macro-level reweighting specifically targeting low-frequency items in contrastive learning for recommendation.

Findings

FACL achieves up to 3.8% improvement in recommendation accuracy.

FACL significantly reduces performance drop on low-frequency items and users.

FACL outperforms existing data and model augmentation methods across five benchmark datasets.

Abstract

In this paper, we revisited the role of data augmentation in contrastive learning for sequential recommendation, revealing its inherent bias against low-frequency items and sparse user behaviors. To address this limitation, we proposed FACL, a frequency-aware adaptive contrastive learning framework that introduces micro-level adaptive perturbation to protect the integrity of rare items, as well as macro-level reweighting to amplify the influence of sparse and rare-interaction sequences during training. Comprehensive experiments on five public benchmark datasets demonstrated that FACL consistently outperforms state-of-the-art data augmentation and model augmentation-based methods, achieving up to 3.8% improvement in recommendation accuracy. Moreover, fine-grained analyses confirm that FACL significantly alleviates the performance drop on low-frequency items and users, highlighting its robust intent-preserving ability and its superior applicability to real-world, long-tail recommendation scenarios.