arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新，休息一下吧，周末愉快~~
arXiv 2111.12840physics.data-ancs.LGhep-exphysics.ins-det
收藏

解释机器学习粒子流重建

Explaining machine-learned particle-flow reconstruction

University of California San Diego（加利福尼亚大学圣迭戈分校）；National Institute of Chemical Physics and Biophysics (NICPB)（化学物理与生物物理研究所）；European Organization for Nuclear Research (CERN)（欧洲核子研究中心）；California Institute of Technology（加利福尼亚理工学院）

Farouk Mokhtar, Raghav Kansal, Daniel Diaz, Javier Duarte, Joosep Pata, Maurizio Pierini, Jean-Roch Vlimant

备注：
5 pages, 3 figures. Accepted to Machine Learning for Physical Sciences NeurIPS 2021 workshop
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

粒子流（PF）算法被用于通用粒子探测器中，通过结合来自不同子探测器的信息来重建碰撞的全面粒子级视图。一个图形神经网络（GNN）模型，被称为机器学习粒子流（MLPF）算法，已被开发，以取代基于规则的PF算法。然而，理解模型的决策并不简单，特别是考虑到集到集预测任务、动态图构建和消息传递步骤的复杂性。在本文中，我们将分层相关传播技术应用于GNNs，并将其应用于MLPF算法，以衡量其预测的相关节点和特征。通过这个过程，我们可以深入了解模型的决策过程。

英文摘要：

The particle-flow (PF) algorithm is used in general-purpose particle detectors to reconstruct a comprehensive particle-level view of the collision by combining information from different subdetectors. A graph neural network (GNN) model, known as the machine-learned particle-flow (MLPF) algorithm, has been developed to substitute the rule-based PF algorithm. However, understanding the model's decision making is not straightforward, especially given the complexity of the set-to-set prediction task, dynamic graph building, and message-passing steps. In this paper, we adapt the layerwise-relevance propagation technique for GNNs and apply it to the MLPF algorithm to gauge the relevant nodes and features for its predictions. Through this process, we gain insight into the model's decision-making.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑