提升自动竞价性能，通过跨序列建模与约束学习优化决策过程
C2:Cross learning module enhanced decision transformer with Constraint-aware loss for auto-bidding
- 引入交叉注意力模块增强状态、动作与回报序列的关联建模
- 设计约束感知损失，在预算和单次转化成本下选择最优策略
- 在AuctionNet数据集上表现优于现有方法，最高提升3.2%
决策变换器（DT）在生成式自动竞价中展现出潜力，能够捕捉时间依赖关系，但存在两大关键缺陷：状态、动作与未来回报（RTG）序列间交叉相关性建模不足，以及对最优与非最优行为无差别学习。为此，我们提出C2框架，包含两项核心创新：(1) 通过交叉注意力机制构建交叉学习块（CLB），强化多序列间的关联建模；(2) 设计约束感知损失（CL），融入预算与每次转化成本（CPA）约束，实现对最优轨迹的选择性学习。在AuctionNet数据集上的大量离线评估显示，C2在不同预算设置下均取得稳定性能提升，最高达3.2%；消融实验验证了CLB与CL的互补协同作用，证明其在自动竞价任务中的优越性。代码已开源：https://github.com/Dingjinren/C2。
原文摘要 · Abstract (English)
Decision Transformer (DT) shows promise for generative auto-bidding by capturing temporal dependencies, but suffers from two critical limitations: insufficient cross-correlation modeling among state, action, and return-to-go (RTG) sequences, and indiscriminate learning of optimal/suboptimal behaviors. To address these, we propose C2, a novel framework enhancing DT with two core innovations: (1) a Cross Learning Block (CLB) via cross-attention to strengthen inter-sequence correlation modeling; (2) a Constraint-aware Loss (CL) incorporating budget and Cost-Per-Acquisition (CPA) constraints for selective learning of optimal trajectories. Extensive offline evaluations on the AuctionNet dataset demonstrate consistent performance gains (up to 3.2% over state-of-the-art method) across diverse budget settings; ablation studies verify the complementary synergy of CLB and CL, confirming C2's superiority in auto-bidding. The code for reproducing our results is available at: https://github.com/Dingjinren/C2.
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。