用神经解码约束优化广告推荐，兼顾收益与体验。
Constraint-Aware Generative Re-ranking for Multi-Objective Optimization in Advertising Feeds
- 统一生成与奖励评估，端到端优化广告排序。
- 在线测试显示收入与用户参与度双提升，延迟达标。
- 适合需要高效率约束优化的工业级推荐系统。
广告推荐中的重排优化是受约束的组合问题，需同时最大化平台收益并保障用户体验。现有生成式排序方法通过自回归解码实现列表级优化，但部署受限于高推理延迟和约束处理能力不足。本文提出一种约束感知的生成式重排框架，将约束优化转化为有界神经解码。不同于以往将生成器与评估器分离的方法，本框架将序列生成与奖励估计统一于单一网络。进一步引入约束感知奖励剪枝，将约束满足直接嵌入解码过程，高效生成最优序列。在大规模工业级广告流上的实验及在线A/B测试表明，该方法在满足严格延迟要求的前提下，提升了收益与用户参与度，为受约束的列表级优化提供了高效的神经解决方案。
原文摘要 · Abstract (English)
Optimizing reranking in advertising feeds is a constrained combinatorial problem, requiring simultaneous maximization of platform revenue and preservation of user experience. Recent generative ranking methods enable listwise optimization via autoregressive decoding, but their deployment is hindered by high inference latency and limited constraint handling. We propose a constraint-aware generative reranking framework that transforms constrained optimization into bounded neural decoding. Unlike prior approaches that separate generator and evaluator models, our framework unifies sequence generation and reward estimation into a single network. We further introduce constraint-aware reward pruning, integrating constraint satisfaction directly into decoding to efficiently generate optimal sequences. Experiments on large-scale industrial feeds and online A/B tests show that our method improves revenue and user engagement while meeting strict latency requirements, providing an efficient neural solution for constrained listwise optimization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。