基于解耦广告商画像与无训练适应的自动出价

中文摘要 AI 辅助

自动出价是现代广告系统的关键组成部分，它为每个广告商提供个性化的出价策略。通过刻画每个个体，基于画像的方法实现了个性化，并在推荐等领域被证明是有效的。然而，尽管广告商的出价行为多种多样，但它们在自动出价中的应用仍然有限。一个主要原因是构建和利用广告商画像面临若干挑战：提取纯画像并非易事，同时建模公共信息和私有信息是困难的，并且画像更新和冷启动适应仍然具有挑战性。为了解决这些问题，我们提出了ADAPT，一个具有解耦广告商画像和无训练适应的自动出价框架。ADAPT引入了一个两阶段训练范式，并支持无训练适应。具体来说，(i) 第一阶段通过广告商记忆库上的对比学习提取纯静态和动态画像；(ii) 第二阶段将动态画像解耦为公共画像和私有画像，并将它们与静态画像结合，共同调节出价策略；(iii) 一旦训练完成，ADAPT无需重新训练即可为新广告商构建画像并更新现有广告商的画像。我们在大规模自动出价基准上的实验表明，ADAPT始终取得优越的性能，消融研究进一步验证了每个模块的有效性。源代码将在该https URL发布。

英文摘要

Auto-bidding is a key component of modern advertising systems that provides a personalized bidding strategy for each advertiser. By characterizing each individual, profile-based methods achieve personalization and have proven effective in domains such as recommendation. However, despite the diverse bidding behavior of advertisers, their application to auto-bidding remains limited. A primary reason is that constructing and leveraging advertiser profiles face several challenges: extracting pure profiles is non-trivial, modeling common and private information simultaneously is difficult, and profile updating and cold-start adaptation remain challenging. To tackle these issues, we propose \textbf{ADAPT}, an \underline{\textbf{A}}uto-bidding framework with \underline{\textbf{D}}isentangled \underline{\textbf{A}}dvertiser \underline{\textbf{P}}rofiles and \underline{\textbf{T}}raining-free adaptation. ADAPT introduces a two-stage training paradigm and supports training-free adaptation. Specifically, (i) the stage 1 extracts pure static and dynamic profiles via contrastive learning over the advertiser memory bank; (ii) the stage 2 disentangles the dynamic profile into a common profile and a private profile, and combines them with the static profile to jointly condition the bidding strategy; (iii) once trained, ADAPT constructs profiles for new advertisers and updates profiles of existing advertisers without retraining. Our experiments on a large-scale auto-bidding benchmark demonstrate that ADAPT consistently achieves superior performance, and ablation studies further validate the effectiveness of each module. The source code will be released at https://github.com/YuzunoKawori/ADAPT.

发表机构

• University of Electronic Science and Technology of China（电子科技大学）
• Taobao & Tmall Group, Alibaba（淘宝天猫集团，阿里巴巴）
• Hainan University（海南大学）

机构由 AI 辅助整理，请以论文原文为准。