FAESRec: Frequency Adaptive Encoder for Sequential Recommendation
Open Access
- 13 November 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (8) , 1-33
Abstract
Sequential recommender systems predominantly focus on time-domain modeling, overlooking rich seasonal and periodic structures revealed in the frequency domain. While recent frequency-aware methods leverage Fourier transforms, their reliance on fixed filters introduces two critical limitations: (i) inadequate sequence encoding due to indiscriminate spectral suppression, causing information degradation, and (ii) semantic-degrading contrastive augmentations that compromise critical frequency components essential for behavioral semantics. To address these challenges, we propose FAESRec, a Frequency Adaptive Encoder with three synergistic innovations: First, a Frequency Adaptive Mixture-of-Experts (FAMoE) layer decomposes sequences into non-overlapping spectral bands with end-to-end learned boundaries, enabling dynamic weighting of heterogeneous frequency drivers. Second, a Filter-Enhanced module (FAFe) employs learnable global/local filters with adaptive thresholds to denoise spectral components while preserving energy-concentrated bands. The filtered spectral features are projected back to the time domain and encoded by a Mamba block. Third, a Frequency Semantic-aware Contrastive Learner (FSaCL) synthesizes semantically coherent views through probabilistic frequency masking, theoretically guaranteeing mutual information conservation between original and augmented sequences. Extensive experiments on six benchmarks from Amazon, Movielens, and LastFM demonstrate FAESRec’s consistent superiority over 13 SOTA baselines. It achieves significant improvements of 2.74–67.69% HR@1 and 3.95–20.38% NDCG@5, particularly under extreme sparsity. Theoretical analysis proves that FSaCL preserves minimal sufficient semantics, establishing a new paradigm for frequency-aware sequential recommendation. Code is available at: https://github.com/0-1user/FAESRec .Keywords
Funding Information
- National Natural Science Foundation of China (61962061 and 62362069)
- Yunnan Fundamental Research Projects (202401BF070001-024)
- Open Fund of Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence
- Open Project Program of Yunnan Key Laboratory of Intelligent Systems and Computing (ISC24Y05)
- Yunnan University School of ISE Graduate Student Scientific Research Project (ISEGS2026B01)
This publication has 78 references indexed in Scilit:
- A survey of sequential recommendation systems: Techniques, evaluation, and future directionsInformation Systems, 2024
- Feature-Aware Contrastive Learning With Bidirectional Transformers for Sequential RecommendationIEEE Transactions on Knowledge and Data Engineering, 2023
- Self-Supervised Learning for Recommender Systems: A SurveyIEEE Transactions on Knowledge and Data Engineering, 2023
- Contrastive Learning with Frequency Domain for Sequential RecommendationApplied Soft Computing, 2023
- Diversifying Collaborative Filtering via Graph Spreading Network and Selective SamplingIEEE Transactions on Neural Networks and Learning Systems, 2023
- Modeling and predicting user preferences with multiple item attributes for sequential recommendationsKnowledge-Based Systems, 2022
- Attention-based Frequency-aware Multi-scale Network for Sequential RecommendationApplied Soft Computing, 2022
- SSE-PT: Sequential Recommendation Via Personalized Transformer2020
- The MovieLens DatasetsACM Transactions on Interactive Intelligent Systems, 2015
- Understanding user behavior in online social networks: a surveyIEEE Communications Magazine, 2013