# S2-CAR: Segmentation-Supervised Complexity-Adaptive Recommendation

Source: [S2-CAR: Segmentation-Supervised Complexity-Adaptive Recommendation](<https://www.sota2.com/research/paper/6a3cb64a206542251d7ca788>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-26T05:00:04.995Z

Authors: Linjiang Guo, Nitin Bisht, Shiqing Wu, Xianzhi Wang, Guandong Xu

Published: 2026-06-24T05:24:18.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Sequential Recommendation on Amazon (R@5, MRR@5, R@10, MRR@10)](<https://www.sota2.com/research/sota/sequential-recommendation-on-amazon-r-at-5-mrr-at-5-r-at-10-mrr-at-10.md>): Sequential Recommendation; AMAZON; R@5: 4.04.

- [Sequential Recommendation on Steam (R@K, MRR@K)](<https://www.sota2.com/research/sota/sequential-recommendation-on-steam-r-at-k-mrr-at-k.md>): Sequential Recommendation; Steam; R@5: 10.84.

- [Sequential Recommendation on ML-1M](<https://www.sota2.com/research/sota/sequential-recommendation-on-ml-1m.md>): Sequential Recommendation; ML 1M; NDCG@10: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.25415>)

[PDF](<https://arxiv.org/pdf/2606.25415.pdf>)
