📒
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
  • Editing Neural Networks
  • Reference:

Was this helpful?

Editable Neural Networks

ICLR 2020 8-22-2020

PreviousTowards Fast Adaptation of Neural Architectures with Meta LearningNextANIL (Almost No Inner Loop)

Last updated 4 years ago

Was this helpful?

Motivation

it is crucially important to correct model mistakes quickly as they appear during training the neural network. In this work, we investigate the problem of neural network editing — how one can efficiently patch a mistake of the model on a particular sample, without influencing the model behavior on other samples. Namely, we propose Editable Training, a model-agnostic training technique that encourages fast editing of the trained model.

Editing Neural Networks

  • f(x,θ)f(x,\theta) f(x,θ) : a neural network

  • Lbase(θ)\mathcal{L}_{base}(\theta)Lbase​(θ) : task-specific objective loss function

The goal is to change model's predictions on a subset of inputs, corresponding to misclassified objects, without affecting other inputs, by changing the model parameters θ\thetaθ .

An editor function could be used to formalized this: θ^=Edit(θ,le)\hat{\theta}=Edit(\theta,l_e)θ^=Edit(θ,le​) , with a constraint: le(θ^)≤0l_e(\hat{\theta})\leq0le​(θ^)≤0

  • θ^\hat{\theta}θ^ is the changed parameters

For example, multi-class classification.

  • le(θ^)=max⁡yi(log⁡p(yi∣x,θ^)−log⁡p(yref∣x,θ^))l_e(\hat{\theta}) = \max_{y_i} (\log p(y_i|x, \hat{\theta}) - \log p(y_{ref}|x,\hat{\theta}))le​(θ^)=maxyi​​(logp(yi​∣x,θ^)−logp(yref​∣x,θ^)) where yrefy_{ref}yref​ is the desired label.

if under the constraint: le(θ^)≤0l_e(\hat{\theta})\leq0le​(θ^)≤0 ,

The constraint: le(θ^)≤0l_e(\hat{\theta})\leq0le​(θ^)≤0 is satisfied iff arg⁡max⁡yilog⁡p(yi∣x,θ^)=yref\arg \max_{y_i} \log p(y_i|x, \hat{\theta})=y_{ref}argmaxyi​​logp(yi​∣x,θ^)=yref​

So the goal is how to design the editor neural network.

Reference:

  • https://openreview.net/forum?id=HJedXaEtvS

  • https://github.com/editable-ICLR2020/editable

  • https://github.com/xtinkt/editable