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
  • [41] TOOLS AND TASKS FOR LEARNING AND META-LEARNING
    Jaworski, Barbara
    JOURNAL OF MATHEMATICS TEACHER EDUCATION, 2005, 8 (05) : 359 - 361
  • [42] Social-Aware Distributed Meta-Learning: A Perspective of Constrained Graphical Bandits
    Wang, Shangshang
    Bian, Simeng
    Tang, Yinxu
    Shao, Ziyu
    ICC 2023-IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS, 2023, : 4385 - 4390
  • [43] On meta-learning rule learning heuristics
    Janssen, Frederik
    Fuernkranz, Johannes
    ICDM 2007: PROCEEDINGS OF THE SEVENTH IEEE INTERNATIONAL CONFERENCE ON DATA MINING, 2007, : 529 - 534
  • [44] Distributed Reptile Algorithm for Meta-Learning Over Multi-Agent Systems
    Zhang, Xianyang
    Hu, Chen
    He, Bing
    Han, Zhiguo
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2022, 70 : 5443 - 5456
  • [45] Using Meta-Learning to predict student performance in virtual learning environments
    Ángel Casado Hidalgo
    Pablo Moreno Ger
    Luis De La Fuente Valentín
    Applied Intelligence, 2022, 52 : 3352 - 3365
  • [46] Differential Evolution and Meta-Learning for Dynamic Ensemble of Neural Network Classifiers
    Lima, Tiago P. F.
    Ludermir, Teresa B.
    2015 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2015,
  • [47] Using Meta-Learning to predict student performance in virtual learning environments
    Hidalgo, Angel Casado
    Ger, Pablo Moreno
    Valentin, Luis De La Fuente
    APPLIED INTELLIGENCE, 2022, 52 (03) : 3352 - 3365
  • [48] Meta-Learning: A Digital Learning Management Framework Using Blockchain for Metaverses
    Golam, Mohtasin
    Tuli, Esmot Ara
    Alief, Revin Naufal
    Kim, Dong-Seong
    Lee, Jae-Min
    IEEE ACCESS, 2024, 12 : 92774 - 92786
  • [49] Landau Theory of Meta-learning
    Plewczynski, Dariusz
    SECURITY AND INTELLIGENT INFORMATION SYSTEMS, 2012, 7053 : 142 - 153
  • [50] Continual meta-learning algorithm
    Mengjuan Jiang
    Fanzhang Li
    Li Liu
    Applied Intelligence, 2022, 52 : 4527 - 4542