arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.20093cs.IR
收藏

ManCAR: 用于序列推荐的流形约束潜在推理与自适应测试时间计算

ManCAR: Manifold-Constrained Latent Reasoning with Adaptive Test-Time Computation for Sequential Recommendation

Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University(多媒体可信感知与高效计算教育部重点实验室,厦门大学);Shopee Pte. Ltd.(虾皮有限公司);School of Informatics, Xiamen University(厦门大学信息学院)

Kun Yang, Yuxuan Zhu, Yazhe Chen, Siyao Zheng, Bangyang Hong, Kangle Wu, Yabo Ni, Anxiang Zeng, Cong Fu, Hui Li

AI总结:

ManCAR通过流形约束和自适应测试时间计算,提升序列推荐的推理精度和稳定性。

摘要:

序列推荐越来越多地使用潜在多步推理来增强测试时间计算。尽管有实证收益,现有方法大多通过目标主导的目标驱动中间推理状态,而没有施加显式的可行性约束。这导致了潜在漂移,即推理轨迹会偏离到不合理的区域。我们主张,有效的推荐推理应被视为在协作流形上的导航,而不是自由形式的潜在细化。为此,我们提出了ManCAR(流形约束自适应推理),一个原理性的框架,该框架将推理扎根于全局交互图的拓扑结构中。ManCAR从用户近期行为的协作邻域构建局部意图先验,表示为一项简单分布。在训练过程中,模型逐步将其潜在预测分布对齐到该先验,迫使推理轨迹保持在有效的流形内。在测试时间,推理会自适应地进行,直到预测分布稳定,从而避免过度细化。我们为ManCAR提供了变分解释,以理论验证其漂预防和自适应测试时间停止机制。在七个基准测试中,实验表明,ManCAR始终优于最先进的基线,相对于NDCG@10实现了高达46.88%的相对改进。我们的代码可在https://github.com/FuCongResearchSquad/ManCAR上获得。

英文摘要:

Sequential recommendation increasingly employs latent multi-step reasoning to enhance test-time computation. Despite empirical gains, existing approaches largely drive intermediate reasoning states via target-dominant objectives without imposing explicit feasibility constraints. This results in latent drift, where reasoning trajectories deviate into implausible regions. We argue that effective recommendation reasoning should instead be viewed as navigation on a collaborative manifold rather than free-form latent refinement. To this end, we propose ManCAR (Manifold-Constrained Adaptive Reasoning), a principled framework that grounds reasoning within the topology of a global interaction graph. ManCAR constructs a local intent prior from the collaborative neighborhood of a user's recent actions, represented as a distribution over the item simplex. During training, the model progressively aligns its latent predictive distribution with this prior, forcing the reasoning trajectory to remain within the valid manifold. At test time, reasoning proceeds adaptively until the predictive distribution stabilizes, avoiding over-refinement. We provide a variational interpretation of ManCAR to theoretically validate its drift-prevention and adaptive test-time stopping mechanisms. Experiments on seven benchmarks demonstrate that ManCAR consistently outperforms state-of-the-art baselines, achieving up to a 46.88% relative improvement w.r.t. NDCG@10. Our code is available at https://github.com/FuCongResearchSquad/ManCAR.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑