> For the complete documentation index, see [llms.txt](https://lichangbin.gitbook.io/paper_notes/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://lichangbin.gitbook.io/paper_notes/meta-learning-representation-for-continual-learning.md).

# Meta-Learning Representation for Continual Learning

## Motivation

Neural Networks trained online on a correlated stream of data suffer from catastrophic forgeting. We propose learning a representation that is robust to forgeting. To learn the representation, we propose OML, a second-order meta-learning objective that directly minimizes interference. Highly sparse representations naturally emerge by minimizing our proposed objective.

Two parts in the model as shown from the figure:

$$\phi\_{\theta}$$  and $$g\_w$$ 

![two parts: RLN and PLN](/files/-MFxIQ5JYNKwGeBjhB7S)

Meta-parameters: A deep neural network that transforms high-dimensional input data to a representation $$\mathcal{R}^d$$ which is more conducive for continual learning

Adaptation parameters: A simple neural network that learns continually from $$\mathcal{R}^d$$ 

#### Meta-Training:

Step 1: adaptation (Inner loop updates only for $$g\_w$$ )

Step 2: compute Meta-Loss on the complete task dataset (similar to MAML)

Step 3: Meta-update: differentiating meta-loss through the adaptation phase (for $$\phi\_\theta$$ and $$g\_w$$ ) \[similar to MAML]

#### Meta-Testing:

Step 1: Adaptation (Inner loop updates only for $$g\_w$$ , use $$\phi\_\theta$$ and $$g\_w$$ learnt from Meta-training)

Step 2: Evaluation (fix $$\phi\_\theta$$ and $$g\_w$$, to compute the accuracy)

#### Note:

* check online meta learning paper again, compare the difference
* attention: domain shift problem 
* two parts architectures: it looks very common in many papers

## Reference:

* <https://papers.nips.cc/paper/8458-meta-learning-representations-for-continual-learning>
* <https://www.youtube.com/watch?v=XlEqFeQiuhk>