Online advertising has become a core revenue driver for the internet industry, with ad auctions playing a crucial role in ensuring platform revenue and advertiser incentives. Traditional auction mechanisms, like GSP, rely on the independent CTR assumption and fail to account for the influence of other displayed items, termed externalities. Recent advancements in learning-based auctions have enhanced the encoding of high-dimensional contextual features. However, existing methods are constrained by the "allocation-after-prediction" design paradigm, which models set-level externalities within candidate ads and fails to consider the sequential context of the final allocation, leading to suboptimal results. This paper introduces the Contextual Generative Auction (CGA), a novel framework that incorporates permutation-level externalities in multi-slot ad auctions. Built on the structure of our theoretically derived optimal solution, CGA decouples the optimization of allocation and payment. We construct an autoregressive generative model for allocation and reformulate the incentive compatibility (IC) constraint into minimizing ex-post regret that supports gradient computation, enabling end-to-end learning of the optimal payment rule. Extensive offline and online experiments demonstrate that CGA significantly enhances platform revenue and CTR compared to existing methods, while effectively approximating the optimal auction with nearly maximal revenue and minimal regret.

翻译：在线广告已成为互联网行业的核心收入来源，而广告拍卖在保障平台收益与广告主激励方面发挥着关键作用。传统拍卖机制（如GSP）依赖独立点击率假设，未能考虑其他展示项目的影响（即外部性）。基于学习的拍卖机制的最新进展加强了对高维上下文特征的编码能力。然而，现有方法受限于"预测后分配"的设计范式，仅在候选广告集合内建模集合级外部性，未能考虑最终分配的序列上下文，导致次优结果。本文提出上下文生成式拍卖（CGA），这是一个在多广告位拍卖中纳入排列级外部性的新型框架。基于理论推导的最优解结构，CGA实现了分配与支付的解耦优化。我们构建了自回归生成模型进行分配决策，并将激励相容（IC）约束重构为最小化支持梯度计算的事后遗憾，从而实现了最优支付规则的端到端学习。大量离线与在线实验表明，相较于现有方法，CGA在平台收入和点击率方面均有显著提升，同时能以近乎最大的收益和最小的遗憾有效逼近最优拍卖机制。