Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance

Autoencoders have useful applications in high energy physics in anomaly detection, particularly for jets—collimated showers of particles produced in collisions such as those at the CERN Large Hadron Collider. We explore the use of graph-based autoencoders, which operate on jets in their “particle cloud” representations and can leverage the interdependencies among the particles within a jet, for such tasks. Additionally, we develop a differentiable approximation to the energy mover’s distance via a graph neural network, which may subsequently be used as a reconstruction loss function for autoencoders.

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

[2]  Marco Cuturi,et al.  Computational Optimal Transport: With Applications to Data Science , 2019 .

[3]  Blaz Bortolato,et al.  Bump Hunting in Latent Space , 2021, ArXiv.

[4]  Maria Spiropulu,et al.  Variational autoencoders for new physics mining at the Large Hadron Collider , 2018, Journal of High Energy Physics.

[5]  O. Amram,et al.  Tag N’ Train: a technique to train improved classifiers on unlabeled data , 2020, Journal of High Energy Physics.

[6]  Katy Craig,et al.  Linearized optimal transport for collider events , 2020, Physical Review D.

[7]  Gianluca Cerminara,et al.  Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics , 2020, Frontiers in Big Data.

[8]  Hao Su,et al.  A Point Set Generation Network for 3D Object Reconstruction from a Single Image , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Nicolas Courty,et al.  POT: Python Optimal Transport , 2021, J. Mach. Learn. Res..

[10]  Joan Bruna,et al.  Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges , 2021, ArXiv.

[11]  Yue Wang,et al.  Dynamic Graph CNN for Learning on Point Clouds , 2018, ACM Trans. Graph..

[12]  Eric A. Moreno,et al.  JEDI-net: a jet identification algorithm based on interaction networks , 2019, The European Physical Journal C.

[13]  Eduardo Rodrigues,et al.  The Scikit-HEP Project , 2019, EPJ Web of Conferences.

[14]  Prabhat,et al.  Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors , 2020, 2003.11603.

[15]  Jonathan Shlomi,et al.  Graph neural networks in particle physics , 2020, Mach. Learn. Sci. Technol..

[16]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[17]  M. Cacciari,et al.  FastJet user manual , 2011, 1111.6097.

[18]  Kyle Cranmer,et al.  Flows for simultaneous manifold learning and density estimation , 2020, NeurIPS.

[19]  Charanjit K. Khosa,et al.  The LHC Olympics 2020 a community challenge for anomaly detection in high energy physics , 2021, Reports on progress in physics. Physical Society.

[20]  J. Monk,et al.  Deep learning as a parton shower , 2018, Journal of High Energy Physics.

[21]  P. Harris,et al.  Pileup per particle identification , 2014, 1407.6013.

[22]  C. Collaboration,et al.  Search for narrow and broad dijet resonances in proton-proton collisions at $\sqrt{s}=$ 13 TeV and constraints on dark matter mediators and other new particles , 2018, 1806.00843.

[23]  Jonathon S. Hare,et al.  FSPool: Learning Set Representations with Featurewise Sort Pooling , 2019, ICLR.

[24]  Abien Fred Agarap.  Deep Learning using Rectified Linear Units (ReLU) , 2018, ArXiv.

[25]  Javier Duarte,et al.  Charged Particle Tracking via Edge-Classifying Interaction Networks , 2021, Computing and Software for Big Science.

[26]  Jan Eric Lenssen,et al.  Fast Graph Representation Learning with PyTorch Geometric , 2019, ArXiv.

[27]  Robert C. Bolles,et al.  Parametric Correspondence and Chamfer Matching: Two New Techniques for Image Matching , 1977, IJCAI.

[28]  Razvan Pascanu,et al.  Relational inductive biases, deep learning, and graph networks , 2018, ArXiv.

[29]  Leonidas J. Guibas,et al.  The Earth Mover's Distance as a Metric for Image Retrieval , 2000, International Journal of Computer Vision.

[30]  D. Shih,et al.  Searching for new physics with deep autoencoders , 2018, Physical Review D.

[31]  Georgios Choudalakis,et al.  On hypothesis testing, trials factor, hypertests and the BumpHunter , 2011, 1101.0390.

[32]  Huilin Qu,et al.  ParticleNet: Jet Tagging via Particle Clouds , 2019, Physical Review D.

[33]  Marco Cuturi,et al.  Sinkhorn Distances: Lightspeed Computation of Optimal Transport , 2013, NIPS.

[34]  Variational Autoencoders for Anomalous Jet Tagging , 2020, 2007.01850.

[35]  Jesse Thaler,et al.  Metric Space of Collider Events. , 2019, Physical review letters.

[36]  Javier Duarte,et al.  Graph Neural Networks for Particle Tracking and Reconstruction , 2020 .

[37]  Yutaro Iiyama,et al.  Learning representations of irregular particle-detector geometry with distance-weighted graph networks , 2019, The European Physical Journal C.

[38]  C. Englert,et al.  Anomaly detection with convolutional Graph Neural Networks , 2021, Journal of High Energy Physics.

[39]  Razvan Pascanu,et al.  Interaction Networks for Learning about Objects, Relations and Physics , 2016, NIPS.