📒
PaperNotes
  • PAPER NOTES
  • Meta-Learning with Implicit Gradient
  • DARTS: Differentiable Architecture Search
  • Meta-Learning of Neural Architectures for Few-Shot Learning
  • Towards Fast Adaptation of Neural Architectures with Meta Learning
  • Editable Neural Networks
  • ANIL (Almost No Inner Loop)
  • Meta-Learning Representation for Continual Learning
  • Learning to learn by gradient descent by gradient descent
  • Modular Meta-Learning with Shrinkage
  • NADS: Neural Architecture Distribution Search for Uncertainty Awareness
  • Modular Meta Learning
  • Sep
    • Incremental Few Shot Learning with Attention Attractor Network
    • Learning Steady-States of Iterative Algorithms over Graphs
      • Experiments
    • Learning combinatorial optimization algorithms over graphs
    • Meta-Learning with Shared Amortized Variational Inference
    • Concept Learners for Generalizable Few-Shot Learning
    • Progressive Graph Learning for Open-Set Domain Adaptation
    • Probabilistic Neural Architecture Search
    • Large-Scale Long-Tailed Recognition in an Open World
    • Learning to stop while learning to predict
    • Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift
    • Learning to Generalize: Meta-Learning for Domain Generalization
  • Oct
    • Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization
    • Network Architecture Search for Domain Adaptation
    • Continuous Meta Learning without tasks
    • Learning Causal Models Online
    • Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
    • Conditional Neural Progress (CNPs)
    • Reviving and Improving Recurrent Back-Propagation
    • Meta-Q-Learning
    • Learning Self-train for semi-supervised few shot classification
    • Watch, Try, Learn: Meta-Learning from Demonstrations and Rewards
  • Nov
    • Neural Process
    • Adversarially Robust Few-Shot Learning: A Meta-Learning Approach
    • Learning to Adapt to Evolving Domains
  • Tutorials
    • Relax constraints to continuous
    • MAML, FO-MAML, Reptile
    • Gradient Descent
      • Steepest Gradient Descent
      • Conjugate Gradient Descent
  • KL, Entropy, MLE, ELBO
  • Coding tricks
    • Python
    • Pytorch
  • ml
    • kmeans
Powered by GitBook
On this page
  • Motivation
  • Reference:

Was this helpful?

Meta-Learning Representation for Continual Learning

NeurIPS 2019 8-24-2020

PreviousANIL (Almost No Inner Loop)NextLearning to learn by gradient descent by gradient descent

Last updated 4 years ago

Was this helpful?

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:

ϕθ\phi_{\theta}ϕθ​ and gwg_wgw​

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

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

Meta-Training:

Step 1: adaptation (Inner loop updates only for gwg_wgw​ )

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 ϕθ\phi_\theta ϕθ​ and gwg_wgw​ ) [similar to MAML]

Meta-Testing:

Step 1: Adaptation (Inner loop updates only for gwg_wgw​ , use ϕθ\phi_\theta ϕθ​ and gwg_wgw​ learnt from Meta-training)

Step 2: Evaluation (fix ϕθ\phi_\theta ϕθ​ and gwg_wgw​, 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
two parts: RLN and PLN