S2-CAR: Segmentation-Supervised Complexity-Adaptive Recommendation

2026-06-24

AI Summary

Existing sequential recommendation methods struggle to accurately capture the complex and heterogeneous user intents due to their reliance on fixed temporal windows or homogeneity assumptions, often leading to misaligned intent boundaries and cross-intent interference. To address this, this work proposes an unsupervised intent segmentation mechanism based on latent energy decay, modeling user intents as continuous latent energy states whose natural decay dynamically triggers segmentation boundaries. A context-aware soft temporal point process (Soft-TPP) is integrated to enable adaptive sequence partitioning. Building upon this, a hierarchical multi-intent aggregation network is designed to adaptively extract and fuse interest representations at multiple granularities. The method is plug-and-play, requiring no pre-specified number of segments, and consistently outperforms 13 baseline models across three public datasets—covering movies, e-commerce, and gaming—with state-of-the-art performance on all evaluation metrics.

Abstract

Sequential recommendation aims to predict user preferences from interaction histories, yet existing models often struggle when behavior patterns become complex and heterogeneous. A key reason is that interaction histories are rarely uniform: users' interests shift in a latent way over time, yet existing models either treat the full sequence as a homogeneous context or rely on rigid time-window segmentation that misaligns with true intent boundaries. This mis-segmentation not only introduces cross-intent interference at intermediate sequence positions but also leads to over-reliance on short-term interest signals. To address this, we propose S2-CAR, a segmentation-supervised and complexity-adaptive framework for sequential recommendation that models user intent as a continuous latent energy state. Specifically, it uses the Context-Aware Soft Temporal Point Process (Soft-TPP) to segment boundaries triggered by the natural decay of latent-state energy rather than fixed intervals, enabling intent segmentation without fixed time-gap rules. Next, upon this segmentation, a Segment-Count-Adaptive Multi-Intent Extraction module hierarchically aggregates intent-coherent segments into a compact set of multi-interest representations. Extensive experiments on 3 representative public benchmark datasets spanning movie, e-commerce, and gaming domains across 13 baselines demonstrate that S2-CAR consistently outperforms state-of-the-art methods across all datasets and metrics. Further analysis shows that the proposed energy-based segmentation serves as a plug-and-play module, yielding consistent improvements when integrated into existing sequential recommendation backbones.

Problem

• sequential recommendation
• intent segmentation
• behavior heterogeneity
• latent intent boundaries
• complex user behavior

Innovation

• Complexity-Adaptive Recommendation
• Energy-Based Segmentation
• Soft Temporal Point Process
• Multi-Intent Extraction
• Sequential Recommendation