MAML, or ModelAgnostic MetaLearning, is a model and taskagnostic algorithm for metalearning that trains a model’s parameters such that a small number of gradient updates will lead to fast learning on a new task.
Consider a model represented by a parametrized function $f_{\theta}$ with parameters $\theta$. When adapting to a new task $\mathcal{T}_{i}$, the model’s parameters $\theta$ become $\theta'_{i}$. With MAML, the updated parameter vector $\theta'_{i}$ is computed using one or more gradient descent updates on task $\mathcal{T}_{i}$. For example, when using one gradient update,
$$ \theta'_{i} = \theta  \alpha\nabla_{\theta}\mathcal{L}_{\mathcal{T}_{i}}\left(f_{\theta}\right) $$
The step size $\alpha$ may be fixed as a hyperparameter or metalearned. The model parameters are trained by optimizing for the performance of $f_{\theta'_{i}}$ with respect to $\theta$ across tasks sampled from $p\left(\mathcal{T}_{i}\right)$. More concretely the metaobjective is as follows:
$$ \min_{\theta} \sum_{\mathcal{T}_{i} \sim p\left(\mathcal{T}\right)} \mathcal{L}_{\mathcal{T_{i}}}\left(f_{\theta'_{i}}\right) = \sum_{\mathcal{T}_{i} \sim p\left(\mathcal{T}\right)} \mathcal{L}_{\mathcal{T_{i}}}\left(f_{\theta  \alpha\nabla_{\theta}\mathcal{L}_{\mathcal{T}_{i}}\left(f_{\theta}\right)}\right) $$
Note that the metaoptimization is performed over the model parameters $\theta$, whereas the objective is computed using the updated model parameters $\theta'$. In effect MAML aims to optimize the model parameters such that one or a small number of gradient steps on a new task will produce maximally effective behavior on that task. The metaoptimization across tasks is performed via stochastic gradient descent (SGD), such that the model parameters $\theta$ are updated as follows:
$$ \theta \leftarrow \theta  \beta\nabla_{\theta} \sum_{\mathcal{T}_{i} \sim p\left(\mathcal{T}\right)} \mathcal{L}_{\mathcal{T_{i}}}\left(f_{\theta'_{i}}\right)$$
where $\beta$ is the meta step size.
Source: ModelAgnostic MetaLearning for Fast Adaptation of Deep NetworksPaper  Code  Results  Date  Stars 

Task  Papers  Share 

MetaLearning  170  36.64% 
FewShot Learning  60  12.93% 
Image Classification  18  3.88% 
reinforcement Learning  16  3.45% 
General Classification  16  3.45% 
FewShot Image Classification  13  2.80% 
Federated Learning  8  1.72% 
Continual Learning  6  1.29% 
Text Classification  6  1.29% 
Component  Type 


🤖 No Components Found  You can add them if they exist; e.g. Mask RCNN uses RoIAlign 