NGA: Non-autoregressive Generative Auction with Global Externalities for Advertising Systems

TL;DR

NGA introduces a non-autoregressive auction framework that models global externalities among ads and content, significantly improving efficiency and effectiveness in online advertising platforms.

Contribution

It presents a novel end-to-end auction framework that explicitly models global externalities and employs non-autoregressive decoding for industrial online advertising.

Findings

Outperforms existing methods in effectiveness and efficiency

Demonstrates superior offline and online performance

Enables real-time, high-quality ad auctions

Abstract

Online advertising auctions are fundamental to internet commerce, demanding solutions that not only maximize revenue but also ensure incentive compatibility, high-quality user experience, and real-time efficiency. While recent learning-based auction frameworks have improved context modeling by capturing intra-list dependencies among ads, they remain limited in addressing global externalities and often suffer from inefficiencies caused by sequential processing. In this work, we introduce the Non-autoregressive Generative Auction with global externalities (NGA), a novel end-to-end framework designed for industrial online advertising. NGA explicitly models global externalities by jointly capturing the relationships among ads as well as the effects of adjacent organic content. To further enhance efficiency, NGA utilizes a non-autoregressive, constraint-based decoding strategy and a parallel multi-tower evaluator for unified list-wise reward and payment computation. Extensive offline experiments and large-scale online A/B testing on commercial advertising platforms demonstrate that NGA consistently outperforms existing methods in both effectiveness and efficiency.