Expert-Guided Diffusion Planner for Auto-Bidding
This work improves auto-bidding for advertisers by integrating expert guidance and skip-step sampling, offering an incremental enhancement to existing diffusion-based methods.
The paper tackled the problem of generating optimal decision sequences in auto-bidding by addressing limitations in diffusion models, such as lack of personalized structural information and timeliness risks, resulting in an 11.29% increase in conversions and 12.36% growth in revenue compared to the baseline.
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.