Influencer Loss: End-to-end Geometric Representation Learning for Track Reconstruction

被引:0
|
作者
Murnane, Daniel [1 ]
机构
[1] Lawrence Berkeley Natl Lab, Berkeley, CA 94720 USA
来源
26TH INTERNATIONAL CONFERENCE ON COMPUTING IN HIGH ENERGY AND NUCLEAR PHYSICS, CHEP 2023 | 2024年 / 295卷
关键词
D O I
10.1051/epjconf/202429509016
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Significant progress has been made in applying graph neural networks (GNNs) and other geometric ML ideas to the track reconstruction problem. State-of-the-art results are obtained using approaches such as the Exatrkx pipeline, which currently applies separate edge construction, classification and segmentation stages. One can also treat the problem as an object condensation task, and cluster hits into tracks in a single stage, such as in the GravNet architecture. However, condensation with such an architecture may still require non-differentiable operations, and arbitrary post-processing. In this work, I extend the ideas of geometric attention to the task of fully geometric (and therefore fully differentiable) end-to-end track reconstruction in a single step. To realize this goal, I introduce a novel condensation loss function called Influencer Loss, which allows an embedded representation of tracks to be learned in tandem with the most representative hit(s) in each track. This loss has global optima that formally match the task of track reconstruction, namely smooth condensation of tracks to a single point, and I demonstrate this empirically on the TrackML dataset. The model not only significantly outperforms the physics performance of the baseline model, it is up to an order of magnitude faster in inference.
引用
收藏
页数:8
相关论文
共 50 条
  • [11] End-to-End Representation Learning for Chemical-Chemical Interaction Prediction
    Kwon, Sunyoung
    Yoon, Sungroh
    IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, 2019, 16 (05) : 1436 - 1447
  • [12] ACTIVEMATCH: END-TO-END SEMI-SUPERVISED ACTIVE REPRESENTATION LEARNING
    Yuan, Xinkai
    Li, Zilinghan
    Wang, Gaoang
    2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2022, : 1136 - 1140
  • [13] Spatial and temporal learning representation for end-to-end recording device identification
    Zeng, Chunyan
    Zhu, Dongliang
    Wang, Zhifeng
    Wu, Minghu
    Xiong, Wei
    Zhao, Nan
    EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2021, 2021 (01)
  • [14] END-TO-END BINARY REPRESENTATION LEARNING VIA DIRECT BINARY EMBEDDING
    Liu, Liu
    Rahimpour, Alireza
    Taalimi, Ali
    Qi, Hairong
    2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 1257 - 1261
  • [15] End-to-end Reinforcement Learning of Robotic Manipulation with Robust Keypoints Representation
    Wang, Tianying
    Puang, En Yen
    Lee, Marcus
    Jing, Wei
    Wu, Yan
    PROCEEDINGS OF 2022 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2022, : 590 - 597
  • [16] An End-to-End Multiplex Graph Neural Network for Graph Representation Learning
    Liang, Yanyan
    Zhang, Yanfeng
    Gao, Dechao
    Xu, Qian
    IEEE ACCESS, 2021, 9 : 58861 - 58869
  • [17] End-to-End Efficient Representation Learning via Cascading Combinatorial Optimization
    Jeong, Yeonwoo
    Kim, Yoonsung
    Song, Hyun Oh
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 11371 - 11379
  • [18] End-to-end Video-level Representation Learning for Action Recognition
    Zhu, Jiagang
    Zhu, Zheng
    Zou, Wei
    2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2018, : 645 - 650
  • [19] End-to-end Autonomous Driving Perception with Sequential Latent Representation Learning
    Chen, Jianyu
    Xu, Zhuo
    Tomizuka, Masayoshi
    2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2020, : 1999 - 2006
  • [20] On Track of Sigfox Confidentiality with End-to-End Encryption
    Fujdiak, Radek
    Blazek, Petr
    Mikhaylov, Konstantin
    Malina, Lukas
    Mlynek, Petr
    Misurec, Jiri
    Blazek, Vojtech
    13TH INTERNATIONAL CONFERENCE ON AVAILABILITY, RELIABILITY AND SECURITY (ARES 2018), 2019,