PuSH - Publication Server of Helmholtz Zentrum München

Kahn, J.* ; Tsaklidis, I.* ; Taubert, O.* ; Reuter, L.* ; Dujany, G.* ; Boeckh, T.* ; Thaller, A.* ; Goldenzweig, P.* ; Bernlochner, F.* ; Streit, A.* ; Götz, M.*

Learning tree structures from leaves for particle decay reconstruction.

Mach. Learn.: Sci. Technol. 3:035012 (2022)
Publ. Version/Full Text DOI
Open Access Gold
Creative Commons Lizenzvertrag
In this work, we present a neural approach to reconstructing rooted tree graphs describing hierarchical interactions, using a novel representation we term the lowest common ancestor generations (LCAG) matrix. This compact formulation is equivalent to the adjacency matrix, but enables learning a tree’s structure from its leaves alone without the prior assumptions required if using the adjacency matrix directly. Employing the LCAG therefore enables the first end-to-end trainable solution which learns the hierarchical structure of varying tree sizes directly, using only the terminal tree leaves to do so. In the case of high-energy particle physics, a particle decay forms a hierarchical tree structure of which only the final products can be observed experimentally, and the large combinatorial space of possible trees makes an analytic solution intractable. We demonstrate the use of the LCAG as a target in the task of predicting simulated particle physics decay structures using both a Transformer encoder and a neural relational inference encoder graph neural network. With this approach, we are able to correctly predict the LCAG purely from leaf features for a maximum tree-depth of 8 in 92.5 % of cases for trees up to 6 leaves (including) and 59.7 % for trees up to 10 in our simulated dataset.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Journal article
Document type Scientific Article
Corresponding Author
Keywords Particle Physics ; Tree Reconstruction ; Lowest Common Ancestor Generation ; Graph Neural Networks ; Self-attention Neural Networks ; Transformer
ISSN (print) / ISBN 2632-2153
e-ISSN 2632-2153
Journal Machine Learning: Science and Technology
Quellenangaben Volume: 3, Issue: 3, Pages: , Article Number: 035012 Supplement: ,
Publisher Institute of Physics Publishing (IOP)
Non-patent literature Publications
Reviewing status Peer reviewed
Institute(s) Helmholtz AI - KIT (HAI - KIT)
Helmholtz AI - HMGU (HAI - HMGU)