Open AccessPosted Content
Meta-Learning with Latent Embedding Optimization
Andrei Rusu,Dushyant Rao,Jakub Sygnowski,Oriol Vinyals,Razvan Pascanu,Simon Osindero,Raia Hadsell +6 more
Reads0
Chats0
TLDR
In this article, a data-dependent latent generative representation of model parameters is learned and a gradient-based meta-learning is performed in a low-dimensional latent space for few-shot learning.Abstract:
Gradient-based meta-learning techniques are both widely applicable and proficient at solving challenging few-shot learning and fast adaptation problems. However, they have practical difficulties when operating on high-dimensional parameter spaces in extreme low-data regimes. We show that it is possible to bypass these limitations by learning a data-dependent latent generative representation of model parameters, and performing gradient-based meta-learning in this low-dimensional latent space. The resulting approach, latent embedding optimization (LEO), decouples the gradient-based adaptation procedure from the underlying high-dimensional space of model parameters. Our evaluation shows that LEO can achieve state-of-the-art performance on the competitive miniImageNet and tieredImageNet few-shot classification tasks. Further analysis indicates LEO is able to capture uncertainty in the data, and can perform adaptation more effectively by optimizing in latent space.read more
Citations
More filters
Journal ArticleDOI
Meta-IP: An Imbalanced Processing Model Based on Meta-Learning for IT Project Extension Forecasts
TL;DR: A Meta-IP model based on transferable knowledge bases with few-shot learning and a model-agnostic meta-learning improvement algorithm to solve the problems of sample scarcity and data imbalance is proposed.
Posted Content
Mutual-Information Based Few-Shot Classification.
TL;DR: Transductive Infomation Maximization (TIM) as discussed by the authors maximizes the mutual information between the query features and their label predictions for a given few-shot task, in conjunction with a supervision loss based on the support set.
Journal ArticleDOI
Smooth Mathematical Function from Compact Neural Networks
TL;DR: In this article , a new activation function integrated sigmoid linear unit (ISLU) was proposed for regression, and a new batch concept "meta-batch" was introduced to improve the performance of neural networks.
Posted Content
Fairness-Aware Online Meta-learning
TL;DR: In this paper, the authors proposed a novel online meta-learning algorithm, namely FFML, which is under the setting of unfairness prevention, to learn good priors of an online fair classification model's primal and dual parameters that are associated with the model's accuracy and fairness.
Journal ArticleDOI
Policy Dispersion in Non-Markovian Environment
TL;DR: In this paper , a policy dispersion scheme is designed for seeking diverse policy representation in a non-Markovian environment, where a transformer-based method is adopted to learn policy embeddings.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.