构建宇宙学多尺度数据集，推动几何深度学习研究
CosmoBench: A Multiscale, Multiview, Multitask Cosmology Benchmark for Geometric Deep Learning
- 整合三尺度暗物质晕与星系点云、两时间尺度合并树数据
- 34000个点云与25000个有向树，支持参数预测、速度估计等任务
- 提供基准模型，促进机器学习与宇宙学融合创新
宇宙学模拟生成大量点云和有向树形式的数据。本文介绍CosmoBench，一个从先进宇宙学模拟中整理的基准数据集，其模拟耗时超过4100万核小时，生成数据量超2拍字节。该数据集是同类中规模最大的：包含34,000个不同尺度的暗物质晕与星系点云，以及25,000个记录晕形成历史的有向树。数据可用于多个任务——从点云和合并树预测宇宙学参数、从集体位置预测单个晕与星系的速度，以及从粗粒度时间尺度重建细粒度合并树。我们提供了若干基线模型，包括基于经典宇宙学建模的方法和基于机器学习的方法。后者涵盖从仅依赖对称性约束的简单线性模型，到计算量巨大的图神经网络等深度学习架构。结果显示，少量不变特征的最小二乘拟合有时优于参数更多、训练时间更长的深度模型。尽管如此，通过结合机器学习与宇宙学，仍有巨大潜力提升现有基线性能。CosmoBench为大规模推进宇宙学与几何深度学习的融合奠定基础。数据集已开放获取，地址：https://cosmobench.streamlit.app
原文摘要 · Abstract (English)
Cosmological simulations provide a wealth of data in the form of point clouds and directed trees. A crucial goal is to extract insights from this data that shed light on the nature and composition of the Universe. In this paper we introduce CosmoBench, a benchmark dataset curated from state-of-the-art cosmological simulations whose runs required more than 41 million core-hours and generated over two petabytes of data. CosmoBench is the largest dataset of its kind: it contains 34 thousand point clouds from simulations of dark matter halos and galaxies at three different length scales, as well as 25 thousand directed trees that record the formation history of halos on two different time scales. The data in CosmoBench can be used for multiple tasks -- to predict cosmological parameters from point clouds and merger trees, to predict the velocities of individual halos and galaxies from their collective positions, and to reconstruct merger trees on finer time scales from those on coarser time scales. We provide several baselines on these tasks, some based on established approaches from cosmological modeling and others rooted in machine learning. For the latter, we study different approaches -- from simple linear models that are minimally constrained by symmetries to much larger and more computationally-demanding models in deep learning, such as graph neural networks. We find that least-squares fits with a handful of invariant features sometimes outperform deep architectures with many more parameters and far longer training time. Still there remains tremendous potential to improve these baselines by combining machine learning and cosmology to fully exploit the data. CosmoBench sets the stage for bridging cosmology and geometric deep learning at scale. We invite the community to push the frontier of scientific discovery by engaging with this dataset, available at https://cosmobench.streamlit.app
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。