Optimised Graph Convolution for Calorimetry Event Classification

TL;DR

This paper introduces an optimized graph convolution framework tailored for particle identification and energy regression in high granularity calorimeters, addressing computational challenges in high energy physics data analysis.

Contribution

It presents a novel graph construction algorithm for resource-constrained environments and implements specialized convolution and pooling layers for calorimetry data.

Findings

Achieved high accuracy in particle identification and energy regression

Demonstrated efficiency of the optimized graph construction method

Applicable to various high granularity detector challenges

Abstract

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 with current methods and algorithms. Graph convolution networks, have been shown to be powerful tools to address these challenges. We present our graph convolution framework for particle identification and energy regression in high granularity calorimeters. In particular, we introduce our algorithm for optimised graph construction in resource constrained environments. We also introduce our implementation of graph convolution and pooling layers. We observe satisfying accuracies, and discuss possible application to other high granularity particle detector challenges.