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
  • [21] A Deep Learning-Based End-To-End CT Reconstruction Method
    Lu, K.
    Ren, L.
    Yin, F.
    MEDICAL PHYSICS, 2020, 47 (06) : E507 - E508
  • [22] End-to-End Reconstruction-Classification Learning for Face Forgery Detection
    Cao, Junyi
    Ma, Chao
    Yao, Taiping
    Chen, Shen
    Ding, Shouhong
    Yang, Xiaokang
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 4103 - 4112
  • [23] Loss Prediction: End-to-End Active Learning Approach For Speech Recognition
    Luo, Jian
    Wang, Jianzong
    Cheng, Ning
    Xiao, Jing
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [24] End-to-End Learning for Multimodal Emotion Recognition in Video With Adaptive Loss
    Huynh, Van Thong
    Yang, Hyung-Jeong
    Lee, Guee-Sang
    Kim, Soo-Hyung
    IEEE MULTIMEDIA, 2021, 28 (02) : 59 - 66
  • [25] End-to-End Incremental Learning
    Castro, Francisco M.
    Marin-Jimenez, Manuel J.
    Guil, Nicolas
    Schmid, Cordelia
    Alahari, Karteek
    COMPUTER VISION - ECCV 2018, PT XII, 2018, 11216 : 241 - 257
  • [26] On end-to-end analysis of packet loss
    Räisänen, VI
    COMPUTER COMMUNICATIONS, 2003, 26 (14) : 1693 - 1697
  • [27] HIMap: HybrId Representation Learning for End-to-end Vectorized HD Map Construction
    Zhu, Yi
    Zhang, Hui
    Yu, Jiaqian
    Yang, Yifan
    Jung, Sangil
    Park, Seung-In
    Yoon, Byung-In
    2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2024, : 15396 - 15406
  • [28] Deep End-to-End Representation Learning for Food Type Recognition from Speech
    Sertolli, Benjamin
    Cummins, Nicholas
    Sengur, Abdulkadir
    Schuller, Bjorn W.
    ICMI'18: PROCEEDINGS OF THE 20TH ACM INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION, 2018, : 574 - 578
  • [29] End-to-end deep representation learning for time series clustering: a comparative study
    Baptiste Lafabregue
    Jonathan Weber
    Pierre Gançarski
    Germain Forestier
    Data Mining and Knowledge Discovery, 2022, 36 : 29 - 81
  • [30] End-to-end wind turbine wake modelling with deep graph representation learning
    Li, Siyi
    Zhang, Mingrui
    Piggott, Matthew D.
    APPLIED ENERGY, 2023, 339