# Learning cosmology and clustering with cosmic graphs

arXiv: https://arxiv.org/abs/2204.13713 · HTML: https://mlsanity.com/paper/2204.13713/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 64 references that are in the map.
- First posted on arXiv 28 Apr 2022.

## Builds on (most cited first, 3 of 3)

- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [The CAMELS Multifield Dataset: Learning the Universe's Fundamental Parameters with Artificial Intelligence](https://mlsanity.com/paper/2109.10915/) (2021)
- [Inferring halo masses with Graph Neural Networks](https://mlsanity.com/paper/2111.08683/) (2021)

## Built on by (most cited first, 16 of 16)

- [The Cosmic Graph: Optimal Information Extraction from Large-Scale Structure using Catalogues](https://mlsanity.com/paper/2207.05202/) (2022)
- [Field Level Neural Network Emulator for Cosmological N-body Simulations](https://mlsanity.com/paper/2206.04594/) (2022)
- [Robust Field-level Likelihood-free Inference with Galaxies](https://mlsanity.com/paper/2302.14101/) (2023)
- [Multiscale Flow for Robust and Optimal Cosmological Analysis](https://mlsanity.com/paper/2306.04689/) (2023)
- [Domain Adaptive Graph Neural Networks for Constraining Cosmological Parameters Across Multiple Data Sets](https://mlsanity.com/paper/2311.01588/) (2023)
- [Robust field-level inference with dark matter halos](https://mlsanity.com/paper/2209.06843/) (2022)
- [The CAMELS project: Expanding the galaxy formation model space with new ASTRID and 28-parameter TNG and SIMBA suites](https://mlsanity.com/paper/2304.02096/) (2023)
- [How DREAMS are made: Emulating Satellite Galaxy and Subhalo Populations with Diffusion Models and Point Clouds](https://mlsanity.com/paper/2409.02980/) (2024)
- [A Cosmic-Scale Benchmark for Symmetry-Preserving Data Processing](https://mlsanity.com/paper/2410.20516/) (2024)
- [Cosmology from Galaxy Redshift Surveys with PointNet](https://mlsanity.com/paper/2211.12346/) (2022)
- [Field-level simulation-based inference with galaxy catalogs: the impact of systematic effects](https://mlsanity.com/paper/2310.15234/) (2023)
- [Diffusion-HMC: Parameter Inference with Diffusion-model-driven Hamiltonian Monte Carlo](https://mlsanity.com/paper/2405.05255/) (2024)
- [CosmoBench: A Multiscale, Multiview, Multitask Cosmology Benchmark for Geometric Deep Learning](https://mlsanity.com/paper/2507.03707/) (2025)
- [A Graph-Based Modeling Framework for Tracing Hydrological Pollutant Transport in Surface Waters](https://mlsanity.com/paper/2302.04991/) (2023)
- [Cosmology with Persistent Homology: Parameter Inference via Machine Learning](https://mlsanity.com/paper/2412.15405/) (2024)
- [Galaxy Phase-Space and Field-Level Cosmology: The Strength of Semi-Analytic Models](https://mlsanity.com/paper/2512.10222/) (2025)

## Abstract (arXiv)

We train deep learning models on thousands of galaxy catalogues from the state-of-the-art hydrodynamic simulations of the CAMELS project to perform regression and inference. We employ Graph Neural Networks (GNNs), architectures designed to work with irregular and sparse data, like the distribution of galaxies in the Universe. We first show that GNNs can learn to compute the power spectrum of galaxy catalogues with a few percent accuracy. We then train GNNs to perform likelihood-free inference at the galaxy-field level. Our models are able to infer the value of Omegarm m with a ~12%-13% accuracy just from the positions of ~1000 galaxies in a volume of (25~h-1rm Mpc)3 at z=0 while accounting for astrophysical uncertainties as modelled in CAMELS. Incorporating information from galaxy properties, such as stellar mass, stellar metallicity, and stellar radius, increases the accuracy to 4%-8%. Our models are built to be translational and rotational invariant, and they can extract information from any scale larger than the minimum distance between two galaxies. However, our models are not completely robust: testing on simulations run with a different subgrid physics than the ones used for training does not yield as accurate results.