Stochastic Primal-Dual Decoding for Multiobjective Generative Recommender Systems

用于多目标生成式推荐系统的随机原始-对偶解码方法

Abstract: Recent advances in recommender systems (RS) have shown substantial performance gains through generative modelling. In practice, recommendation often involves constructing slates — ordered lists of items — that must satisfy multiple objectives beyond relevance, such as constraints defined over item attributes or fairness constraints. 摘要： 推荐系统（RS）的最新进展表明，通过生成式建模可以显著提升性能。在实践中，推荐通常涉及构建“列表”（slate）——即有序的物品列表——这些列表必须满足相关性之外的多个目标，例如基于物品属性的约束或公平性约束。

Existing multiobjective approaches either rely on post-processing techniques designed for non-generative settings, or incorporate auxiliary objectives directly into model training. The former does not explicitly account for the sequential nature of generative RS, while the latter is often impractical in large-scale systems. 现有的多目标方法要么依赖于为非生成式场景设计的后处理技术，要么直接将辅助目标纳入模型训练中。前者没有明确考虑生成式推荐系统的序列特性，而后者在大规模系统中往往不切实际。

We propose a lightweight, inference-time decoding layer that augments autoregressive generative RS to support multiobjective slate generation without modifying or retraining the underlying model. We formulate decoding as an online constrained optimisation problem, where items are selected sequentially, and trade-offs between relevance and auxiliary objectives are adjusted dynamically based on the remaining constraint slack, i.e., how much of each objective remains to be satisfied. 我们提出了一种轻量级的推理时解码层，它增强了自回归生成式推荐系统，使其能够在不修改或重新训练底层模型的情况下支持多目标列表生成。我们将解码过程表述为一个在线约束优化问题，其中物品被顺序选择，且相关性与辅助目标之间的权衡会根据剩余的约束松弛度（即每个目标还有多少未被满足）进行动态调整。

This is implemented via a stochastic primal-dual approximation scheme that balances relevance and auxiliary objectives during generation. We provide theoretical guarantees on constraint violation and regret, and evaluate the proposed approach through extensive offline experiments and a large-scale online A/B experiment in a real-world recommender system. 该方法通过一种随机原始-对偶近似方案实现，在生成过程中平衡了相关性和辅助目标。我们为约束违规和遗憾（regret）提供了理论保证，并通过广泛的离线实验以及在真实推荐系统中的大规模在线 A/B 测试评估了所提出的方法。

Our results show consistent improvements in multiobjective trade-offs, including a +1.8% gain in the auxiliary objectives achieved at zero cost to user satisfaction. 我们的结果显示，多目标权衡方面取得了持续的改进，包括在不牺牲用户满意度的情况下，辅助目标提升了 1.8%。