用神经网络动态分配资源，平衡公平与效率，提升系统利用率。
Trading Utility for Dynamic Fairness in Multiple Resource Division with Sequential Demand
- 设计可微分的公平性损失函数，实现多目标优化
- 在保持公平性的同时，利用率显著提升，展现帕累托改进
- 适合共享计算环境中的实时资源调度场景
动态多资源分配是共享计算环境中的核心问题，用户需求按序到达，需在未知未来需求的情况下公平分配资源。现有方法强调公平性保障，如共享激励、无嫉妒性与动态帕累托最优，但常忽略系统效用。这些公平性准则相互冲突，难以同时严格满足。本文提出一种神经分配机制，通过序列展开中的多目标优化调和公平性与效用。首先，基于步骤损失函数形式化动态场景下的公平性，支持可微训练。利用非浪费性，将解空间约束于需求子空间，并允许资源剩余时弹性超分配。实验表明，所学分配器在保持相近公平性水平下，效用显著提升，揭示了各指标间的清晰帕累托前沿式权衡。
原文摘要 · Abstract (English)
Dynamic multi-resource allocation is a central problem in shared computing environments, where users' demands arrive sequentially and resources must be distributed fairly without knowledge of future demands. Existing methods emphasize fairness guarantees such as Sharing Incentive, Envy Freeness, and Dynamic Pareto Optimality, but often overlook system utility. Moreover, these fairness criteria are mutually incompatible, preventing strict enforcement of them at the same time. We propose a neural allocation mechanism that reconciles fairness with utility through multi-objective optimization during sequential rollout. We first formalize fairness in the dynamic setting via stepwise loss functions for Sharing Incentive, Envy Freeness, and Dynamic Pareto Optimality, enabling differentiable training. Leveraging non-wastefulness, we parameterized the solutions by constraining allocations to the subspace of demand while allowing elastic over-allocation when resources remain available. Empirical results demonstrate that our learned allocator achieves substantially higher utility at comparable levels of fairness, uncovering clear Pareto-frontier-like tradeoffs across metrics.
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。