Frequency-aware Adaptive Contrastive Learning for Sequential Recommendation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Zhikai, Zhang, Weihua
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908785234149376
author Wang, Zhikai
Zhang, Weihua
author_facet Wang, Zhikai
Zhang, Weihua
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17057
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Frequency-aware Adaptive Contrastive Learning for Sequential Recommendation
Wang, Zhikai
Zhang, Weihua
Information Retrieval
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.
title Frequency-aware Adaptive Contrastive Learning for Sequential Recommendation
topic Information Retrieval
url https://arxiv.org/abs/2601.17057