循环点击率：释放循环缩放技术在点击率预测中的潜力

摘要

基于Transformer的点击率（CTR）预测模型通过堆叠更多参数实现规模化时，会带来持续增长的计算与存储开销，导致模型扩展雄心与严苛的工业部署约束之间的鸿沟日益扩大。我们提出LoopCTR模型，引入循环扩展范式，通过共享模型层的递归复用增强训练阶段计算量，实现计算量与参数增长的解耦。该模型采用超连接残差结构和专家混合机制增强的三明治架构，并在每个循环深度实施过程监督，将多循环优势编码至共享参数中。这种"训练多循环-推理零循环"策略使得单次前向传播（无需任何循环）即可超越所有基线模型。在三个公开基准和一个工业数据集上的实验表明，该模型实现了最先进的性能。预言机分析进一步揭示了0.02-0.04 AUC的未开发潜力空间，且训练循环次数较少的模型展现出更高的预言机上界，这为自适应推理指明了富有前景的发展方向。

English

Scaling Transformer-based click-through rate (CTR) models by stacking more parameters brings growing computational and storage overhead, creating a widening gap between scaling ambitions and the stringent industrial deployment constraints. We propose LoopCTR, which introduces a loop scaling paradigm that increases training-time computation through recursive reuse of shared model layers, decoupling computation from parameter growth. LoopCTR adopts a sandwich architecture enhanced with Hyper-Connected Residuals and Mixture-of-Experts, and employs process supervision at every loop depth to encode multi-loop benefits into the shared parameters. This enables a train-multi-loop, infer-zero-loop strategy where a single forward pass without any loop already outperforms all baselines. Experiments on three public benchmarks and one industrial dataset demonstrate state-of-the-art performance. Oracle analysis further reveals 0.02--0.04 AUC of untapped headroom, with models trained with fewer loops exhibiting higher oracle ceilings, pointing to a promising frontier for adaptive inference.

循环点击率：释放循环缩放技术在点击率预测中的潜力

LoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate Prediction

摘要

Support