Multi-agent Auto-Bidding with Latent Graph Diffusion Models
This work addresses auto-bidding in competitive auction environments, which is an incremental advancement for domains like online advertising.
The paper tackled the problem of optimizing bidding strategies in large-scale multi-agent auctions under constraints, proposing a diffusion-based framework that improved auto-bidding performance across multiple key performance indicator metrics in empirical evaluations.
This paper proposes a diffusion-based auto-bidding framework that leverages graph representations to model large-scale auction environments. In such settings, agents must dynamically optimize bidding strategies under constraints defined by key performance indicator (KPI) metrics, all while operating in competitive environments characterized by uncertain, sparse, and stochastic variables. To address these challenges, we introduce a novel approach combining learnable graph-based embeddings with a planning-based latent diffusion model (LDM). By capturing patterns and nuances underlying the interdependence of impression opportunities and the multi-agent dynamics of the auction environment, the graph representation enable expressive computations regarding auto-bidding outcomes. With reward alignment techniques, the LDM's posterior is fine-tuned to generate auto-bidding trajectories that maximize KPI metrics while satisfying constraint thresholds. Empirical evaluations on both real-world and synthetic auction environments demonstrate significant improvements in auto-bidding performance across multiple common KPI metrics, as well as accuracy in forecasting auction outcomes.