Imperial College London

ProfessorMichaelBronstein

Faculty of EngineeringDepartment of Computing

Chair in Machine Learning and Pattern Recognition
 
 
 
//

Contact

 

m.bronstein Website

 
 
//

Location

 

569Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Choma:2019:10.1109/ICMLA.2018.00064,
author = {Choma, N and Monti, F and Gerhardt, L and Palczewski, T and Ronaghi, Z and Prabhat, P and Bhimji, W and Bronstein, M and Klein, S and Bruna, J},
doi = {10.1109/ICMLA.2018.00064},
pages = {386--391},
title = {Graph Neural Networks for IceCube Signal Classification},
url = {http://dx.doi.org/10.1109/ICMLA.2018.00064},
year = {2019}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - © 2018 IEEE. Tasks involving the analysis of geometric (graph-and manifold-structured) data have recently gained prominence in the machine learning community, giving birth to a rapidly developing field of geometric deep learning. In this work, we leverage graph neural networks to improve signal detection in the IceCube neutrino observatory. The IceCube detector array is modeled as a graph, where vertices are sensors and edges are a learned function of the sensors spatial coordinates. As only a subset of IceCubes sensors is active during a given observation, we note the adaptive nature of our GNN, wherein computation is restricted to the input signal support. We demonstrate the effectiveness of our GNN architecture on a task classifying IceCube events, where it outperforms both a traditional physics-based method as well as classical 3D convolution neural networks.
AU - Choma,N
AU - Monti,F
AU - Gerhardt,L
AU - Palczewski,T
AU - Ronaghi,Z
AU - Prabhat,P
AU - Bhimji,W
AU - Bronstein,M
AU - Klein,S
AU - Bruna,J
DO - 10.1109/ICMLA.2018.00064
EP - 391
PY - 2019///
SP - 386
TI - Graph Neural Networks for IceCube Signal Classification
UR - http://dx.doi.org/10.1109/ICMLA.2018.00064
ER -