针对推荐系统中的数据稀疏问题，提出自适应测试时增强方法，按用户行为动态选择最优增强策略。
Beyond One-Size-Fits-All: Adaptive Test-Time Augmentation for Sequential Recommendation
- 基于强化学习构建自适应增强框架，为每条用户序列动态选择最优增强操作。
- 在四个真实数据集上验证，相对最佳固定策略提升最高达26.31%。
- 无需重训练模型，计算开销小，适合部署在各类推荐系统中。
测试时增强（TTA）已成为缓解序列推荐中数据稀疏问题的有前景方法，能在不需昂贵模型重训练的情况下提升推理精度。然而，现有方法通常采用统一、与用户无关的增强策略。本文首次实证表明，这种“一刀切”设计本质上次优，因忽略了用户间行为的显著异质性，且不同特征的用户序列其最优增强操作差异显著。为此，我们提出AdaTTA，一种即插即用的基于强化学习的自适应推理框架，可按序列粒度学习选择特定增强操作。将增强选择建模为马尔可夫决策过程，引入具有混合状态表示的演员-评论家网络及联合宏排序奖励设计，以动态确定每条输入序列的最优操作。在四个真实世界数据集和两种推荐主干模型上的大量实验表明，AdaTTA始终优于最佳固定策略基线，在Home数据集上相对提升高达26.31%，同时仅带来适度的计算开销。
原文摘要 · Abstract (English)
Test-time augmentation (TTA) has become a promising approach for mitigating data sparsity in sequential recommendation by improving inference accuracy without requiring costly model retraining. However, existing TTA methods typically rely on uniform, user-agnostic augmentation strategies. We show that this "one-size-fits-all" design is inherently suboptimal, as it neglects substantial behavioral heterogeneity across users, and empirically demonstrate that the optimal augmentation operators vary significantly across user sequences with different characteristics for the first time. To address this limitation, we propose AdaTTA, a plug-and-play reinforcement learning-based adaptive inference framework that learns to select sequence-specific augmentation operators on a per-sequence basis. We formulate augmentation selection as a Markov Decision Process and introduce an Actor-Critic policy network with hybrid state representations and a joint macro-rank reward design to dynamically determine the optimal operator for each input user sequence. Extensive experiments on four real-world datasets and two recommendation backbones demonstrate that AdaTTA consistently outperforms the best fixed-strategy baselines, achieving up to 26.31% relative improvement on the Home dataset while incurring only moderate computational overhead
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。