Meta-Consolidation for Continual Learning

• URL: http://arxiv.org/abs/2010.00352v1
• Date: Thu, 1 Oct 2020 12:34:35 GMT
• Title: Meta-Consolidation for Continual Learning
• Authors: K J Joseph and Vineeth N Balasubramanian
• Abstract summary: We present a novel methodology for continual learning called MERLIN: Meta-Consolidation for Continual Learning. We operate in the challenging online continual learning setting, where a data point is seen by the model only once. Our experiments with continual learning benchmarks of MNIST, CIFAR-10, CIFAR-100 and Mini-ImageNet datasets show consistent improvement over five baselines.
• Score: 36.054541200030705
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The ability to continuously learn and adapt itself to new tasks, without losing grasp of already acquired knowledge is a hallmark of biological learning systems, which current deep learning systems fall short of. In this work, we present a novel methodology for continual learning called MERLIN: Meta-Consolidation for Continual Learning. We assume that weights of a neural network $\boldsymbol \psi$, for solving task $\boldsymbol t$, come from a meta-distribution $p(\boldsymbol{\psi|t})$. This meta-distribution is learned and consolidated incrementally. We operate in the challenging online continual learning setting, where a data point is seen by the model only once. Our experiments with continual learning benchmarks of MNIST, CIFAR-10, CIFAR-100 and Mini-ImageNet datasets show consistent improvement over five baselines, including a recent state-of-the-art, corroborating the promise of MERLIN.

Related papers

• Improving Representational Continuity via Continued Pretraining [76.29171039601948]
  Transfer learning community (LP-FT) outperforms naive training and other continual learning methods. LP-FT also reduces forgetting in a real world satellite remote sensing dataset (FMoW) variant of LP-FT gets state-of-the-art accuracies on an NLP continual learning benchmark.
  arXiv  Detail & Related papers  (2023-02-26T10:39:38Z)
• NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networks [6.205922305859479]
  NISPA architecture forms stable paths to preserve learned knowledge from older tasks. NISPA significantly outperforms state-of-the-art continual learning baselines.
  arXiv  Detail & Related papers  (2022-06-18T04:56:49Z)
• Hypernetworks for Continual Semi-Supervised Learning [37.109190308781244]
  We propose a framework for semi-supervised continual learning called Meta-Consolidation for Continual Semi-Supervised Learning (MCSSL) Our framework has a hypernetwork that learns the meta-distribution that generates the weights of a semi-supervised auxiliary classifier generative adversarial network $(textitSemi-ACGAN)$ as the base network. We present $textitSemi-Split CIFAR-10$, a new benchmark for continual semi-supervised learning, obtained by modifying the $textitSplit CIFAR-10$ dataset.
  arXiv  Detail & Related papers  (2021-10-05T07:42:38Z)
• Generalising via Meta-Examples for Continual Learning in the Wild [24.09600678738403]
  We develop a novel strategy to deal with neural networks that "learn in the wild" We equip it with MEML - Meta-Example Meta-Learning - a new module that simultaneously alleviates catastrophic forgetting. We extend it by adopting a technique that creates various augmented tasks and optimises over the hardest.
  arXiv  Detail & Related papers  (2021-01-28T15:51:54Z)
• Online Structured Meta-learning [137.48138166279313]
  Current online meta-learning algorithms are limited to learn a globally-shared meta-learner. We propose an online structured meta-learning (OSML) framework to overcome this limitation. Experiments on three datasets demonstrate the effectiveness and interpretability of our proposed framework.
  arXiv  Detail & Related papers  (2020-10-22T09:10:31Z)
• Meta-Learning in Neural Networks: A Survey [4.588028371034406]
  This survey describes the contemporary meta-learning landscape. We first discuss definitions of meta-learning and position it with respect to related fields. We then propose a new taxonomy that provides a more comprehensive breakdown of the space of meta-learning methods.
  arXiv  Detail & Related papers  (2020-04-11T16:34:24Z)
• iTAML: An Incremental Task-Agnostic Meta-learning Approach [123.10294801296926]
  Humans can continuously learn new knowledge as their experience grows. Previous learning in deep neural networks can quickly fade out when they are trained on a new task. We introduce a novel meta-learning approach that seeks to maintain an equilibrium between all encountered tasks.
  arXiv  Detail & Related papers  (2020-03-25T21:42:48Z)
• Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning [74.07455280246212]
  Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. We show that current continual learning, meta-learning, meta-continual learning, and continual-meta learning techniques fail in this new scenario. We propose Continual-MAML, an online extension of the popular MAML algorithm as a strong baseline for this scenario.
  arXiv  Detail & Related papers  (2020-03-12T15:47:16Z)
• Automated Relational Meta-learning [95.02216511235191]
  We propose an automated relational meta-learning framework that automatically extracts the cross-task relations and constructs the meta-knowledge graph. We conduct extensive experiments on 2D toy regression and few-shot image classification and the results demonstrate the superiority of ARML over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2020-01-03T07:02:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.