提出全局有序生成流网络，解决多目标优化中的冲突问题。
Global-Order GFlowNets
- 用全局顺序替代局部顺序，避免优化目标冲突。
- 在多个基准上实现更高效多样采样，逼近帕累托前沿。
- 适合需要无标量化的复杂多目标优化场景。
有序保持（OP）生成流网络在使用随机优化技术解决复杂的多目标黑箱优化问题方面表现出色，能够在线训练以高效采样接近帕累托前沿的多样化候选解。其核心优势在于基于帕累托支配关系对训练样本施加局部顺序，无需像偏好条件生成流网络那样进行标量化解析。然而我们发现，局部顺序的引入可能导致优化目标之间的冲突。为此，本文提出全局有序生成流网络，将局部顺序转化为全局顺序，从而解决此类冲突。在多个基准上的实验评估表明，所提方法具有有效性和前景。
原文摘要 · Abstract (English)
Order-Preserving (OP) GFlowNets have demonstrated remarkable success in tackling complex multi-objective (MOO) black-box optimization problems using stochastic optimization techniques. Specifically, they can be trained online to efficiently sample diverse candidates near the Pareto front. A key advantage of OP GFlowNets is their ability to impose a local order on training samples based on Pareto dominance, eliminating the need for scalarization - a common requirement in other approaches like Preference-Conditional GFlowNets. However, we identify an important limitation of OP GFlowNets: imposing a local order on training samples can lead to conflicting optimization objectives. To address this issue, we introduce Global-Order GFlowNets, which transform the local order into a global one, thereby resolving these conflicts. Our experimental evaluations on various benchmarks demonstrate the efficacy and promise of our proposed method.
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。