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

Autor:	Thais, Savannah, Murnane, Daniel
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning High Energy Physics - Experiment
Druh dokumentu:	Working Paper
Popis:	Incorporating inductive biases into ML models is an active area of ML research, especially when ML models are applied to data about the physical world. Equivariant Graph Neural Networks (GNNs) have recently become a popular method for learning from physics data because they directly incorporate the symmetries of the underlying physical system. Drawing from the relevant literature around group equivariant networks, this paper presents a comprehensive evaluation of the proposed benefits of equivariant GNNs by using real-world particle physics reconstruction tasks as an evaluation test-bed. We demonstrate that many of the theoretical benefits generally associated with equivariant networks may not hold for realistic systems and introduce compelling directions for future research that will benefit both the scientific theory of ML and physics applications. Comment: Paper at Knowledge and Logical Reasoning in the Era of Data-driven Learning Workshop at ICML 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2311.03094 Zobrazit plný text záznamu View this record from Arxiv