用专家轨迹指导扩散模型，提升广告自动出价的转化率和收益
Expert-Guided Diffusion Planner for Auto-Bidding
- 引入专家轨迹引导扩散生成，避免纯回报优化的偏差
- 跳步采样策略提升生成效率，减少时间风险
- 在线测试显示转化率提升11.29%，收入增12.36%
自动出价在广告系统中广泛应用，服务于多样化广告主。生成式出价因其强大的规划能力和泛化性日益受到关注，不依赖马尔可夫决策过程（MDP），在长周期场景下表现更优。条件扩散建模在自动出价领域展现出显著潜力。然而，仅以回报为优化标准无法保证生成真正最优的决策序列，因缺乏个性化结构信息。此外，扩散模型的自回归生成机制固有时间延迟风险。为此，本文提出一种新型条件扩散建模方法，融合专家轨迹引导与跳步采样策略，提升生成效率。离线实验全面验证了该方法的有效性，并通过在线A/B测试进一步证实：相比基线，转化率提升11.29%，收入增长12.36%。
原文摘要 · Abstract (English)
Auto-bidding is widely used in advertising systems, serving a diverse range of advertisers. Generative bidding is increasingly gaining traction due to its strong planning capabilities and generalizability. Unlike traditional reinforcement learning-based bidding, generative bidding does not depend on the Markov Decision Process (MDP), thereby exhibiting superior planning performance in long-horizon scenarios. Conditional diffusion modeling approaches have shown significant promise in the field of auto-bidding. However, relying solely on return as the optimality criterion is insufficient to guarantee the generation of truly optimal decision sequences, as it lacks personalized structural information. Moreover, the auto-regressive generation mechanism of diffusion models inherently introduces timeliness risks. To address these challenges, we introduce a novel conditional diffusion modeling approach that integrates expert trajectory guidance with a skip-step sampling strategy to improve generation efficiency. The efficacy of this method has been demonstrated through comprehensive offline experiments and further substantiated by statistically significant outcomes in online A/B testing, yielding an 11.29% increase in conversions and a 12.36% growth in revenue relative to the baseline.
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。