UniRec: A Dual Enhancement of Uniformity and Frequency in Sequential Recommendations

TL;DR

UniRec addresses the underexplored roles of sequence uniformity and item frequency in sequential recommendation. It introduces a bidirectional dual-branch architecture—Sequence Enhancement and Item Enhancement—coupled with Multidimensional Time Modeling to better represent non-uniform sequences and less-frequent items. Extensive experiments on four real-world datasets against 11 baselines demonstrate significant gains, with ablation and hyperparameter analyses confirming the contributions of each component. By explicitly leveraging uniformity and frequency, UniRec provides a robust, scalable approach to time-aware sequential recommendations and suggests a new direction for feature augmentation in the field.

Abstract

Representation learning in sequential recommendation is critical for accurately modeling user interaction patterns and improving recommendation precision. However, existing approaches predominantly emphasize item-to-item transitions, often neglecting the time intervals between interactions, which are closely related to behavior pattern changes. Additionally, broader interaction attributes, such as item frequency, are frequently overlooked. We found that both sequences with more uniform time intervals and items with higher frequency yield better prediction performance. Conversely, non-uniform sequences exacerbate user interest drift and less-frequent items are difficult to model due to sparse sampling, presenting unique challenges inadequately addressed by current methods. In this paper, we propose UniRec, a novel bidirectional enhancement sequential recommendation method. UniRec leverages sequence uniformity and item frequency to enhance performance, particularly improving the representation of non-uniform sequences and less-frequent items. These two branches mutually reinforce each other, driving comprehensive performance optimization in complex sequential recommendation scenarios. Additionally, we present a multidimensional time module to further enhance adaptability. To the best of our knowledge, UniRec is the first method to utilize the characteristics of uniformity and frequency for feature augmentation. Comparing with eleven advanced models across four datasets, we demonstrate that UniRec outperforms SOTA models significantly. The code is available at https://github.com/Linxi000/UniRec.

Figures (8)

• Figure 1: An example of uniform and non-uniform sequences in a real dataset.
• Figure 2: The performance of models under different subset partition ratios, with the X-axis representing the percentage of data classified as uniform and frequent.
• Figure 3: Overview framework of Item Enhancement (A), Sequence Enhancement (B), and Multidimensional Time Modeling in Sequential Recommendation (C), using a uniform sequence as an example.
• Figure 4: Overview of inference phase.
• Figure 5: Ablation performance with various enhancements across different subsets from ML-1M.