arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.09761cs.LGastro-ph.COastro-ph.IMcs.AI
收藏

基于图神经网络的无监督资源分配

Unsupervised Resource Allocation with Graph Neural Networks

Princeton University(普林斯顿大学);Fermilab(费米实验室)

Miles Cranmer, Peter Melchior, Brian Nord

摘要:

我们提出了一种方法,通过学习如何在无监督的方式分配资源,以最大限度地提高全球的效用函数。我们希望分配目标之间的相互作用是重要的,因此建议学习奖励结构的GNN接近最优的分配政策。通过放松资源约束,我们可以采用基于梯度的优化,而不是更标准的进化算法。我们的算法的动机是在现代天文学的一个问题,其中一个需要选择有限的初始信息的基础上,在$10^9$星系,其详细的测量将导致最佳的推断宇宙的组成。我们的技术提供了一种灵活的学习分配策略的方法,只需要感兴趣的物理和测量过程的前向模拟器。我们预计,我们的技术也将在一系列的资源分配问题的应用。

英文摘要:

We present an approach for maximizing a global utility function by learning how to allocate resources in an unsupervised way. We expect interactions between allocation targets to be important and therefore propose to learn the reward structure for near-optimal allocation policies with a GNN. By relaxing the resource constraint, we can employ gradient-based optimization in contrast to more standard evolutionary algorithms. Our algorithm is motivated by a problem in modern astronomy, where one needs to select-based on limited initial information-among $10^9$ galaxies those whose detailed measurement will lead to optimal inference of the composition of the universe. Our technique presents a way of flexibly learning an allocation strategy by only requiring forward simulators for the physics of interest and the measurement process. We anticipate that our technique will also find applications in a range of resource allocation problems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑