Neural Message Passing for Jet Physics

Supervised learning has incredible potential for particle physics, and one application that has received a great deal of attention involves collimated sprays of particles called jets. Recent progress for jet physics has leveraged machine learning techniques based on computer vision and natural language processing. In this work, we consider message passing on a graph where the nodes are the particles in a jet. We design variants of a message-passing neural network (MPNN); (1) with a learnable adjacency matrix, (2) with a learnable symmetric adjacency matrix, and (3) with a set2set aggregated hidden state and MPNN with an identity adjacency matrix. We compare these against the previously proposed recursive neural network with a fixed tree structure and show that the MPNN with a learnable adjacency matrix and two message-passing iterations outperforms all the others.

[1]  F. Scarselli,et al.  A new model for learning in graph domains , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[2]  M. Cacciari,et al.  The anti-$k_t$ jet clustering algorithm , 2008, 0802.1189.

[3]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[4]  G. Salam Towards jetography , 2009, 0906.1833.

[5]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[6]  Joan Bruna,et al.  Spectral Networks and Locally Connected Networks on Graphs , 2013, ICLR.

[7]  J. Cogan,et al.  Jet-images: computer vision inspired techniques for jet tagging , 2014, 1407.5675.

[8]  Luke de Oliveira,et al.  Jet-images — deep learning edition , 2015, Journal of High Energy Physics.

[9]  Alán Aspuru-Guzik,et al.  Convolutional Networks on Graphs for Learning Molecular Fingerprints , 2015, NIPS.

[10]  Leandro Giordano Almeida,et al.  Playing tag with ANN: boosted top identification with pattern recognition , 2015, 1501.05968.

[11]  Joan Bruna,et al.  Deep Convolutional Networks on Graph-Structured Data , 2015, ArXiv.

[12]  Patrick T. Komiske,et al.  Deep learning in color: towards automated quark/gluon jet discrimination , 2016, Journal of High Energy Physics.

[13]  Richard S. Zemel,et al.  Gated Graph Sequence Neural Networks , 2015, ICLR.

[14]  P. Baldi,et al.  Jet flavor classification in high-energy physics with deep neural networks , 2016, 1607.08633.

[15]  Rob Fergus,et al.  Learning Multiagent Communication with Backpropagation , 2016, NIPS.

[16]  Vijay S. Pande,et al.  Molecular graph convolutions: moving beyond fingerprints , 2016, Journal of Computer-Aided Molecular Design.

[17]  P. Baldi,et al.  Jet Substructure Classification in High-Energy Physics with Deep Neural Networks , 2016, 1603.09349.

[18]  Mathias Niepert,et al.  Learning Convolutional Neural Networks for Graphs , 2016, ICML.

[19]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[20]  Samy Bengio,et al.  Order Matters: Sequence to sequence for sets , 2015, ICLR.

[21]  Razvan Pascanu,et al.  A simple neural network module for relational reasoning , 2017, NIPS.

[22]  Pierre Vandergheynst,et al.  Geometric Deep Learning: Going beyond Euclidean data , 2016, IEEE Signal Process. Mag..

[23]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[24]  Joan Bruna,et al.  Community Detection with Graph Neural Networks , 2017 .

[25]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

[26]  G. Kasieczka,et al.  Deep-learning top taggers or the end of QCD? , 2017, 1701.08784.

[27]  E. Dawe,et al.  Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks , 2016, 1609.00607.

[28]  Kyunghyun Cho,et al.  QCD-aware recursive neural networks for jet physics , 2017, Journal of High Energy Physics.

[29]  B. Nachman,et al.  Jet substructure at the Large Hadron Collider: A review of recent advances in theory and machine learning , 2017, Physics Reports.