Distributed Evolution Strategies Using TPUs for Meta-Learning

被引:0
|
作者
Sheng, Alex [1 ]
He, Jun Yi Derek [2 ]
机构
[1] NYU, Tandon Sch Engn, New York, NY 10003 USA
[2] Woodlands Coll Pk High Sch, Acad Sci & Technol, The Woodlands, TX USA
关键词
meta-learning; evolution strategies; tpu;
D O I
10.1109/ssci47803.2020.9308334
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Meta-learning traditionally relies on backpropagation through entire tasks to iteratively improve a model's learning dynamics. However, this approach is computationally intractable when scaled to complex tasks. We propose a distributed evolutionary meta-learning strategy using Tensor Processing Units (TPUs) that is highly parallel and scalable to arbitrarily long tasks with no increase in memory cost. Using a Prototypical Network trained with evolution strategies on the Omniglot dataset, we achieved an accuracy of 98.4% on a 5-shot classification problem. Our algorithm used as much as 40 times less memory than automatic differentiation to compute the gradient, with the resulting model achieving accuracy within 1.3% of a backpropagation-trained equivalent (99.6%). We observed better classification accuracy as high as 99.1% with larger population configurations. We further experimentally validate the stability and performance of ES-ProtoNet across a variety of training conditions (varying population size, model size, number of workers, shot, way, ES hyperparameters, etc.). Our contributions are twofold: we provide the first assessment of evolutionary meta-learning in a supervised setting, and create a general framework for distributed evolution strategies on TPUs.
引用
收藏
页码:721 / 728
页数:8
相关论文
共 50 条
  • [21] Few-Shot Classification with Meta-Learning for Urban Infrastructure Monitoring Using Distributed Acoustic Sensing
    Van Luong, Huynh
    Deligiannis, Nikos
    Wilhelm, Roman
    Drapp, Bernd
    SENSORS, 2024, 24 (01)
  • [22] Load forecasting using a multivariate meta-learning system
    Matijas, Marin
    Suykens, Johan A. K.
    Krajcar, Slavko
    EXPERT SYSTEMS WITH APPLICATIONS, 2013, 40 (11) : 4427 - 4437
  • [23] Optimizing Recommendations for Clustering Algorithms Using Meta-Learning
    Jilling, Adam
    Alvarez, Marco
    2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
  • [24] Meta-learning on Flowshop using Fitness Landscape Analysis
    Pavelski, Lucas Marcondes
    Delgado, Myriam Regattieri
    Kessaci, Marie-Eleonore
    PROCEEDINGS OF THE 2019 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO'19), 2019, : 925 - 933
  • [25] Using meta-learning for multi-target regression
    Aguiar, Gabriel J.
    Santana, Everton J.
    de Carvalho, Andre C. P. F. L.
    Barbon Junior, Sylvio
    INFORMATION SCIENCES, 2022, 584 : 665 - 684
  • [26] Choosing instance selection method using meta-learning
    Moura, Shayane de Oliveira
    de Freitas, Marcelo Bassani
    Cardoso, Halisson A. C.
    Cavalcanti, George D. C.
    2014 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC), 2014, : 2003 - 2007
  • [27] Meta-features for meta-learning
    Rivolli, Adriano
    Garcia, Luís P.F.
    Soares, Carlos
    Vanschoren, Joaquin
    de Carvalho, André C.P.L.F.
    Knowledge-Based Systems, 2022, 240
  • [28] Meta-features for meta-learning
    Rivolli, Adriano
    Garcia, Luis P. F.
    Soares, Carlos
    Vanschoren, Joaquin
    de Carvalho, Andre C. P. L. F.
    KNOWLEDGE-BASED SYSTEMS, 2022, 240
  • [29] Meta-Modelling Meta-Learning
    Hartmann, Thomas
    Moawad, Assaad
    Schockaert, Cedric
    Fouquet, Francois
    Le Traon, Yves
    2019 ACM/IEEE 22ND INTERNATIONAL CONFERENCE ON MODEL DRIVEN ENGINEERING LANGUAGES AND SYSTEMS (MODELS 2019), 2019, : 300 - 305
  • [30] Learning Tensor Representations for Meta-Learning
    Deng, Samuel
    Guo, Yilin
    Hsu, Daniel
    Mandal, Debmalya
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 151, 2022, 151