相关论文: Weisfeiler-Lehman Graph Kernel Method: A New Appro…

Chemical tagging has great promise as a technique to unveil our Galaxy's history. Grouping stars based on their similar chemistry can establish details of the star formation and merger history of the Milky Way. With precise measurements of…

Message passing neural networks (MPNNs) have emerged as the most popular framework of graph neural networks (GNNs) in recent years. However, their expressive power is limited by the 1-dimensional Weisfeiler-Lehman (1-WL) test. Some works…

In the era of large-scale spectroscopic surveys in the Local Group (LG), we can explore using chemical abundances of halo stars to study the star formation and chemical enrichment histories of the dwarf galaxy progenitors of the Milky Way…

Message Passing Neural Networks (MPNNs) are a common type of Graph Neural Network (GNN), in which each node's representation is computed recursively by aggregating representations (messages) from its immediate neighbors akin to a…

Previous attempts at segmenting molecular line maps of molecular clouds have focused on using position-position-velocity data cubes of a single line to separate the spatial components of the cloud. In contrast, wide field spectral imaging…

To unravel the structures of C12H12O7 isomers, identified as light-absorbing photooxidation products of syringol in atmospheric chamber experiments, we apply a graph-based molecule generator and machine learning workflow. To accomplish this…

The possibility to constrain cosmological parameters from galaxy surveys using field-level machine learning methods that bypass traditional summary statistics analyses, depends crucially on our ability to generate simulated training sets.…

Recently, a novel two-phase framework named mol-infer for inference of chemical compounds with prescribed abstract structures and desired property values has been proposed. The framework mol-infer is primarily based on using mixed integer…

GALA is a freely distributed Fortran code to derive automatically the atmospheric parameters (temperature, gravity, microturbulent velocity and overall metallicity) and abundances for individual species of stellar spectra using the…

Graph Transformer has recently received wide attention in the research community with its outstanding performance, yet its structural expressive power has not been well analyzed. Inspired by the connections between Weisfeiler-Lehman (WL)…

We estimate chemical abundances and ionization parameters in the nuclear region of a sample of 143 galaxies from the Palomar Spectroscopic Survey, composed by Star-Forming Galaxies (87), Seyferts 2 (16) and LINERs (40) using the…

The combinatorial refinement techniques have proven to be an efficient approach to isomorphism testing for particular classes of graphs. If the number of refinement rounds is small, this puts the corresponding isomorphism problem in a…

A significant fraction of high redshift star-forming disc galaxies are known to host giant clumps, whose nature and role in galaxy evolution are yet to be understood. In this work we first present a new method based on neural networks to…

Applying machine learning to molecules is challenging because of their natural representation as graphs rather than vectors.Several architectures have been recently proposed for deep learning from molecular graphs, but they suffer from…

Modern astronomical surveys are observing spectral data for millions of stars. These spectra contain chemical information that can be used to trace the Galaxy's formation and chemical enrichment history. However, extracting the information…

Various recent proposals increase the distinguishing power of Graph Neural Networks GNNs by propagating features between $k$-tuples of vertices. The distinguishing power of these "higher-order'' GNNs is known to be bounded by the…

Graph problems are fundamentally challenging for large language models (LLMs). While LLMs excel at processing unstructured text, graph tasks require reasoning over explicit structure, permutation invariance, and computationally complex…

Missing node attributes is a common problem in real-world graphs. Graph neural networks have been demonstrated power in graph representation learning while their performance is affected by the completeness of graph information. Most of them…

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…

Graph neural networks (GNNs) are a powerful tool to learn representations on graphs by iteratively aggregating features from node neighbourhoods. Many variant models have been proposed, but there is limited understanding on both how to…