多样性约束下的参数化公平资源分配

中文摘要 AI 辅助

资源在多个智能体组间的分配出现在诸多应用场景中，包括电子商务推荐系统、住房分配及课程分配，这类分配通常被建模为带有多样性约束的优化问题，以保障组间公平性。现有方法通常将这些约束作为硬性条件执行，这会过度限制可行解空间，且常导致分配结果次优。本文提出PRA——一种多样性约束下的公平资源分配参数化框架，受经济模型中风险规避参数使用的启发，PRA引入一组可控制的不平等规避参数，以柔性方式调节组级多样性，从而实现公平性与分配效率间的灵活权衡。通过恰当校准参数，PRA可生成符合指定多样性约束的公平最优分配。为适配特定应用的额外约束，我们进一步将该框架扩展为自适应变体APRA。我们证明，无论选择何种公平性指标及额外约束的性质，PRA和APRA均保持最优性，凸显了所提方法的通用性与鲁棒性。在三个真实世界应用上开展的大量实验表明，所提框架在有效性和鲁棒性上均始终优于现有基准方法。

英文摘要

Resource allocation across multiple agent groups arises in many applications including e-commerce recommendation systems, housing assignment, and course allocation, and is commonly formulated as an optimization problem with diversity constraints to ensure group fairness. Existing approaches typically enforce these constraints as hard conditions, which overly restrict the feasible solution space and often lead to suboptimal allocations. In this paper, we propose PRA, a parameterized framework for fair resource allocation under diversity constraints. Inspired by the use of risk-aversion parameters in economic models, PRA introduces a set of controllable inequality-aversion parameters to softly regulate group-level diversity, thereby enabling flexible trade-offs between fairness and allocation efficiency. With appropriately calibrated parameters, PRA yields fairness-optimal assignments that comply with the specified diversity constraints. To accommodate additional application-specific constraints, we further extend the framework to an adaptive variant, APRA. We establish that the optimality of both PRA and APRA holds regardless of the chosen fairness metric and the nature of the additional constraints, underscoring the generality and robustness of our approach. Extensive experiments on three real-world applications demonstrate that our proposed framework consistently outperforms existing baselines in both effectiveness and robustness.

发表机构

• Huazhong University of Science and Technology（华中科技大学）
• McGill University（麦吉尔大学）
• The University of British Columbia（不列颠哥伦比亚大学）
• National University of Singapore（新加坡国立大学）

机构由 AI 辅助整理，请以论文原文为准。