DP-Rec：面向高效长序列推荐的自适应补丁化方法
DP-Rec: Towards Dynamic Patching for Efficient Long-Sequence Recommendation
浏览论文内容
中文总结 AI 辅助
针对长序列推荐中Transformer计算开销大、噪声敏感的问题，提出DP-Rec动态潜在补丁架构，通过对比熵惊喜分割序列并压缩为动态行为向量，在受限预算下实现更优效率与准确率权衡。
中文摘要 AI 辅助
Transformer通过有效建模动态用户行为和长程依赖，重新定义了序列推荐。然而，它们本质上仍然低效：标准架构以固定速率运行，对用户历史中的每个项目分配相当的计算量，而不考虑其信息内容。这导致在长序列上产生高昂的计算开销，并增加对行为噪声的敏感性。为解决这一问题，从业者常采用有损序列压缩、分阶段建模或截断等方法，这限制了模型在推理时利用长历史完整上下文的能力。受近期Byte Latent Transformer成功的启发，我们提出了DP-Rec，一种用于推荐的动态潜在补丁化架构。DP-Rec从项目级建模转向补丁级建模，通过使用对比熵惊喜来分割交互序列，以识别信息丰富的行为边界。一个轻量级补丁编码器将这些时间上下文化片段压缩为一组减少的动态潜在行为向量，随后由更大的潜在Transformer处理，并解码以进行下一项预测。大量实验表明，在受限计算预算下，DP-Rec能有效扩展到长序列，并在非压缩和固定大小压缩基线上实现了更优的效率-准确率权衡。
英文摘要
Transformers have redefined sequential recommendation by effectively modeling dynamic user behaviors and long-range dependencies. However, they remain inherently inefficient: standard architectures operate at a fixed rate, allocating comparable computation to every item in a user's history regardless of its information content. This leads to prohibitive computational overhead on long sequences and increased sensitivity to behavioral noise. To address this, practitioners often resort to lossy sequence compression, staged modeling, or truncation. This limits the model's ability to leverage the full context of long histories during inference. Inspired by the recent success of Byte Latent Transformer, we propose DP-Rec, a dynamic latent patching architecture for recommendation. DP-Rec shifts from item-level modeling to patch-level modeling by segmenting interaction sequences using contrastive entropy surprise to identify informative behavioral boundaries. A lightweight patch encoder compresses these temporally contextualized segments into a reduced set of dynamic latent behavior vectors, which are then processed by a larger latent transformer and decoded for next-item prediction. Extensive experiments show that, under constrained computational budgets, DP-Rec scales effectively to long sequences and achieves a superior efficiency-accuracy trade-off over both non-compressed and fixed-size compression baselines.
