Related papers: Exploring DHCAL design and performance with Graph …

In the ILD detector, HCAL is inside the coil. The HCAL is about 5 interaction length thick, and ECAL is about 1 interaction length thick. For example, an eighty GeV hadron, it is only 95% energy will be contained in ECAL plus HCAL. We need…

In the recent years, high energy physics discoveries have been driven by the increasing of luminosity and/or detector granularity. This evolution gives access to bigger statistics and data samples, but can make it hard to process results…

The construction of modern detectors used in high-energy physics experiments is typically guided by modeling with the Geant4 toolkit to evaluate detector performance in terms of geometrical acceptance and detection efficiency. Several…

The prediction of configurational disorder properties, such as configurational entropy and order-disorder phase transition temperature, of compound materials relies on efficient and accurate evaluations of configurational energies. Previous…

The transition away from carbon-based energy sources poses several challenges for the operation of electricity distribution systems. Increasing shares of distributed energy resources (e.g. renewable energy generators, electric vehicles) and…

Graph neural networks (GNN) have achieved state-of-the-art performance on various industrial tasks. However, the poor efficiency of GNN inference and frequent Out-Of-Memory (OOM) problem limit the successful application of GNN on edge…

Graph convolutional networks (GCNs) have shown remarkable learning capabilities when processing graph-structured data found inherently in many application areas. GCNs distribute the outputs of neural networks embedded in each vertex over…

Many of today's most interesting questions involve understanding and interpreting complex relationships within graph-based structures. For instance, in materials science, predicting material properties often relies on analyzing the…

Kolmogorov-Arnold Networks represent a recent advancement in machine learning, with the potential to outperform traditional perceptron-based neural networks across various domains as well as provide more interpretability with the use of…

To enable heterogeneous computing systems with autonomous programming and optimization capabilities, we propose a unified, end-to-end, programmable graph representation learning (PGL) framework that is capable of mining the complexity of…

We analyze the photon rates from a hadronic gas in equilibrium using chiral reduction formulas and a density expansion. The chiral reduction is carried to second order in the pion density which in principal includes all kinetic processes of…

The Deep Graph Library (DGL) was designed as a tool to enable structure learning from graphs, by supporting a core abstraction for graphs, including the popular Graph Neural Networks (GNN). DGL contains implementations of all core graph…

The ILD, International Large Detector, is one of the detector concepts for a future linear collider. Its performance is investigated using Monte-Carlo full simulation and PandoraPFA. Among several options, a combination of the…

Neural architecture search (NAS) for Graph neural networks (GNNs), called NAS-GNNs, has achieved significant performance over manually designed GNN architectures. However, these methods inherit issues from the conventional NAS methods, such…

The study of partial differential equations (PDE) through the framework of deep learning emerged a few years ago leading to the impressive approximations of simple dynamics. Graph neural networks (GNN) turned out to be very useful in those…

A new Highly-Granular time-of-flight Neutron Detector (HGND) is being developed and constructed to measure azimuthal neutron flow and neutron yields in nucleus-nucleus interactions in heavy-ion collisions with energies up to 4A GeV in the…

This paper describes the algorithms for the reconstruction and identification of electrons in the central region of the ATLAS detector at the Large Hadron Collider (LHC). These algorithms were used for all ATLAS results with electrons in…

Graph neural networks (GNNs) have demonstrated excellent performance in semi-supervised node classification tasks. Despite this, two primary challenges persist: heterogeneity and heterophily. Each of these two challenges can significantly…

Processing-In-Memory (PIM) architectures offer a promising approach to accelerate Graph Neural Network (GNN) training and inference. However, various PIM devices such as ReRAM, FeFET, PCM, MRAM, and SRAM exist, with each device offering…

Graph neural networks (GNNs) are a class of neural networks that allow to efficiently perform inference on data that is associated to a graph structure, such as, e.g., citation networks or knowledge graphs. While several variants of GNNs…