paper-with-me

Papers

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

2017-03-09 · ICML 2017 8 · Chelsea Finn, Pieter Abbeel, Sergey Levine

We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning. The goal of meta-learning is to train a model on a variety of learning tasks, such that it can solve new learning tasks using only a small number of training samples. In our approach, the parameters of the model are explicitly trained such that a small number of gradient steps with a small amount of training data from a new task will produce good generalization performance on that task. In effect, our method trains the model to be easy to fine-tune. We demonstrate that this approach leads to state-of-the-art performance on two few-shot image classification benchmarks, produces good results on few-shot regression, and accelerates fine-tuning for policy gradient reinforcement learning with neural network policies.

📄 PDF Abstract BibTeX arXiv:1703.03400

Code (85)

cbfinn/maml 공식 구현 tf
cbfinn/maml_rl 공식 구현 tf
2023-MindSpore-4/Code-5/tree/main/MAML mindspore
AntreasAntoniou/HowToTrainYourMAMLPytorch pytorch
ArnoutDevos/maml-cifar-fs tf
BBDrive/Meta-SGD-RL pytorch
CocoJam/MAML tf
GeorgeDUT/MetaRLSAS pytorch
HilbertXu/MAML-Tensorflow tf
JWSoh/MZSR tf
JeonMinkyu/MAML_Pytorch pytorch
KamalM8/Few-Shot-learning-Fashion pytorch
LKLQQ/LEO mindspore
MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Model_Agnostic_Meta_Learning_for_Fast_Adaptation_of_Deep_Networks pytorch
Mind23-2/MindCode-101/tree/main/MAML mindspore
Mind23-2/MindCode-3/tree/main/MAML mindspore
Mind23-2/MindCode-55 mindspore
MoritzTaylor/maml-rl-tf2 tf
Octavio-Pappalardo/MAML_for_RL_pytorch pytorch
PaddlePaddle/PaddleRec/tree/master/models/multitask/maml paddle
Runist/torch_maml pytorch
SinghJasdeep/Projecting-Conflicting-Gradients pytorch
ThomasGoerttler/similarity-analysis-of-maml tf
Tikquuss/meta_XLM pytorch
Zhiwei-Z/PrompLimitTest tf
Zhiwei-Z/SeqPromp tf
Zhiwei-Z/prompzzw tf
alexub/jax-meta-learning jax
aliengirlliv/teachable
andrewbo29/mtm-meta-learning-sa pytorch
antaradas94/MAML-waste-classification
clrrrr/promp_plus tf
code-implementation1/Code5/tree/main/MAML mindspore
crashmoon/MAML-Pytorch-Multi-GPUs pytorch
csyanbin/MAML-Pytorch-Multi-GPUs pytorch
damedollaforthree/nrml pytorch
dkalpakchi/ReproducingSCAPytorch pytorch
dragen1860/MAML-Pytorch pytorch
dragen1860/MAML-Pytorch-RL pytorch
dragen1860/Reptile-Pytorch pytorch
ebadrian/metadl tf
fastforwardlabs/learning-to-learn pytorch
fmu2/PyTorch-MAML pytorch
foolyc/Meta-SGD tf
gcucurull/maml_flax jax
gebob19/REPTILE-Metalearning pytorch
gebob19/cscd94-metalearning pytorch
gebob19/cscd94_metalearning pytorch
hfahrudin/reptile_implement_tf2 tf
hoyeoplee/pytorch-maml pytorch
iclavera/meta-mb tf
ido90/roml-maml pytorch
infinitemugen/MAML-Pytorch pytorch
jonasrothfuss/promp tf
katerakelly/pytorch-maml pytorch
laiviet/maml pytorch
learnables/learn2learn pytorch
leopard-ai/betty pytorch
lgcollins/tr-maml pytorch
lif31up/model-agnostic-meta-learning pytorch
llan-ml/tesp tf
mari-linhares/tensorflow-maml tf
mikehuisman/revisiting-learned-optimizers pytorch
minseop-aitrics/FewshotLearning tf
novicestone/meta-cetm pytorch
nyu-larx/attack_metarl pytorch
oscarknagg/few-shot pytorch
potsawee/maml pytorch
prajjwal1/fluence pytorch
psh150204/MAML pytorch
ray-project/ray/tree/master/rllib
s-a-malik/multi-few pytorch
seblee97/task_weighted_maml jax
shaohua0116/MultiDigitMNIST
sheryl-ai/MetaPred tf
shunzh/pytorch-maml-rl pytorch
sidney1505/arc_maml_transformer tf
stefanowoerner/medimeta-pytorch pytorch
theneuralbeing/maml pytorch
tristandeleu/pytorch-maml pytorch
tristandeleu/pytorch-maml-rl pytorch
xiuyu0000/new_papers_codes/tree/main/MAML mindspore
yaoyao-liu/mini-imagenet-tools tf
yoonholee/MT-net tf
yredwood/fewshot_blogpost tf

Tasks

Category-Agnostic Pose EstimationFew-Shot Image ClassificationFew-Shot LearningGeneral Classificationimage-classificationImage ClassificationMeta-LearningOne-Shot Learningregressionreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

TRPO Trust Region Policy Optimization, or TRPO, is a policy gradient method in reinforcement learning that avoids parameter updates that change the policy too much with a KL…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Batch Normalization 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
MAML 설명 없음

Similar Papers 제목 키워드 기반

Unraveling Model-Agnostic Meta-Learning via The Adaptation Learning Rate

2021-09-29 · ICLR 2022 4 · Yingtian Zou, Fusheng Liu, Qianxiao Li

Model-Agnostic Meta-Learning (MAML) aims to find initial weights that allow fast adaptation to new tasks. The adaptation (inner loop) learning rate in MAML plays a central role in enabling such fast adaptation. However, …

Meta-Learning

Model-Agnostic Meta-Learning using Runge-Kutta Methods

2019-10-16 · Daniel Jiwoong Im, Yibo Jiang, Nakul Verma

Meta-learning has emerged as an important framework for learning new tasks from just a few examples. The success of any meta-learning model depends on (i) its fast adaptation to new tasks, as well as (ii) having a shared…

Meta-LearningmodelReinforcement Learning

Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing

2021-04-10 · ACL 2022 5 · Anna Langedijk, Verna Dankers, Phillip Lippe, Sander Bos 외

Meta-learning, or learning to learn, is a technique that can help to overcome resource scarcity in cross-lingual NLP problems, by enabling fast adaptation to new tasks. We apply model-agnostic meta-learning (MAML) to the…

Dependency ParsingFew-Shot LearningMeta-Learning

Faster Optimization-Based Meta-Learning Adaptation Phase

2022-06-13 · Kostiantyn Khabarlak

Neural networks require a large amount of annotated data to learn. Meta-learning algorithms propose a way to decrease the number of training samples to only a few. One of the most prominent optimization-based meta-learni…

Meta-Learning

On the Importance of Attention in Meta-Learning for Few-Shot Text Classification

2018-06-03 · Xiang Jiang, Mohammad Havaei, Gabriel Chartrand, Hassan Chouaib 외

Current deep learning based text classification methods are limited by their ability to achieve fast learning and generalization when the data is scarce. We address this problem by integrating a meta-learning procedure t…

ClassificationFew-Shot Text ClassificationGeneral ClassificationInductive Bias+7