Federated learning offers a privacy-preserving solution for personalized recommendation by enabling collaborative model training across multiple clients without sharing sensitive user data. However, existing federated recommendation systems still struggle with three intertwined challenges: capturing multi-dimensional user preferences, modeling complex user–item interactions in distributed settings, and balancing the trade-off between privacy protection and recommendation accuracy. To this end, we propose Attention-based Personalized Federated Recommendation (APFR), a novel framework that integrates attention mechanisms to enhance both personalization and contextual understanding. APFR introduces a personalized score function and user embedding strategy to more precisely represent diverse user preferences, while multi-head attention is employed to capture intricate user–item relationships and contextual dependencies. Furthermore, APFR incorporates differential privacy techniques, such as Laplace and Gaussian noise, to ensure robust privacy protection with minimal accuracy loss. Experimental results on benchmark datasets demonstrate that APFR achieves superior performance in recommendation accuracy and privacy preservation, compared to state-of-the-art methods. The code and datasets are available at https://github.com/lyg2618/APFR.

The aim of sequential recommendation (SR) is to predict a user’s next interaction by analyzing their historical behavioral sequences. The proposed framework leverages the inherent symmetry in user behavior patterns, where temporal and spectral representations exhibit complementary structures that can be harmonized for robust recommendation. Conventional SR methods predominantly utilize implicit feedback (e.g., clicks and views) as model inputs, whereby observed interactions are treated as positive instances, while unobserved ones are considered negative samples. However, the inherent randomness and diversity in user behaviors inevitably introduce noise into such implicit feedback, potentially compromising the accuracy of recommendations. Recent studies have explored noise mitigation through two primary approaches: temporal-domain methods that reweight interactions to distill clean samples for comprehensive user preference modeling, and frequency-domain techniques that purify item embeddings to reduce the propagation of noise. While temporal approaches excel in sample refinement, frequency-based methods demonstrate superior capability in learning noise-resistant representations through spectral analysis. Motivated by the desire to synergize these complementary advantages, we propose SR-DFN, a novel framework that systematically addresses noise interference through coordinated time–frequency processing. Self-guided sample purification is implemented in the temporal domain of our architecture via adaptive interaction weighting, effectively distilling behaviorally significant patterns. The refined sequence is then transformed into the frequency domain, where learnable spectral filters operate to further attenuate residual noise components while preserving essential preference signals. Drawing on the convolution theorem’s revelation regarding frequency-domain operations capturing behavioral periodicity, we critically examine conventional position encoding schemes and propose an efficient parameterization strategy that eliminates redundant positional embeddings without compromising temporal awareness. Comprehensive experiments conducted on four real-world benchmark datasets demonstrate SR-DFN’s superior performance over state-of-the-art baselines, with ablation studies validating the effectiveness of our dual-domain denoising mechanism. Our findings suggest that coordinated time–frequency processing offers a principled solution for noise-resilient sequential recommendation while challenging conventional assumptions about positional encoding requirements in spectral-based approaches. The symmetry principles underlying our dual-domain approach demonstrate how the balanced processing of temporal and frequency domains can achieve superior noise resilience.