English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Incorporating inductive biases into ML models is an active area of MLresearch, especially when ML models are applied to data about the physicalworld. Equivariant Graph Neural Networks (GNNs) have recently become a popularmethod for learning from physics data because they directly incorporate thesymmetries of the underlying physical system. Drawing from the relevantliterature around group equivariant networks, this paper presents acomprehensive evaluation of the proposed benefits of equivariant GNNs by usingreal-world particle physics reconstruction tasks as an evaluation test-bed. Wedemonstrate that many of the theoretical benefits generally associated withequivariant networks may not hold for realistic systems and introducecompelling directions for future research that will benefit both the scientifictheory of ML and physics applications.

Equivariance Is Not All You Need: Characterizing the Utility of Equivariant Graph Neural Networks for Particle Physics Tasks