La-MAML: Look-ahead Meta Learning for Continual Learning

• URL: http://arxiv.org/abs/2007.13904v2
• Date: Thu, 12 Nov 2020 02:08:10 GMT
• Title: La-MAML: Look-ahead Meta Learning for Continual Learning
• Authors: Gunshi Gupta, Karmesh Yadav and Liam Paull
• Abstract summary: We propose Look-ahead MAML (La-MAML), a fast optimisation-based meta-learning algorithm for online-continual learning, aided by a small episodic memory. La-MAML achieves performance superior to other replay-based, prior-based and meta-learning based approaches for continual learning on real-world visual classification benchmarks.
• Score: 14.405620521842621
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The continual learning problem involves training models with limited capacity to perform well on a set of an unknown number of sequentially arriving tasks. While meta-learning shows great potential for reducing interference between old and new tasks, the current training procedures tend to be either slow or offline, and sensitive to many hyper-parameters. In this work, we propose Look-ahead MAML (La-MAML), a fast optimisation-based meta-learning algorithm for online-continual learning, aided by a small episodic memory. Our proposed modulation of per-parameter learning rates in our meta-learning update allows us to draw connections to prior work on hypergradients and meta-descent. This provides a more flexible and efficient way to mitigate catastrophic forgetting compared to conventional prior-based methods. La-MAML achieves performance superior to other replay-based, prior-based and meta-learning based approaches for continual learning on real-world visual classification benchmarks. Source code can be found here: https://github.com/montrealrobotics/La-MAML

Related papers

• ConML: A Universal Meta-Learning Framework with Task-Level Contrastive Learning [49.447777286862994]
  ConML is a universal meta-learning framework that can be applied to various meta-learning algorithms. We demonstrate that ConML integrates seamlessly with optimization-based, metric-based, and amortization-based meta-learning algorithms.
  arXiv  Detail & Related papers  (2024-10-08T12:22:10Z)
• EMO: Episodic Memory Optimization for Few-Shot Meta-Learning [69.50380510879697]
  episodic memory optimization for meta-learning, we call EMO, is inspired by the human ability to recall past learning experiences from the brain's memory. EMO nudges parameter updates in the right direction, even when the gradients provided by a limited number of examples are uninformative. EMO scales well with most few-shot classification benchmarks and improves the performance of optimization-based meta-learning methods.
  arXiv  Detail & Related papers  (2023-06-08T13:39:08Z)
• Learning to Learn with Indispensable Connections [6.040904021861969]
  We propose a novel meta-learning method called Meta-LTH that includes indispensible (necessary) connections. Our method improves the classification accuracy by approximately 2% (20-way 1-shot task setting) for omniglot dataset.
  arXiv  Detail & Related papers  (2023-04-06T04:53:13Z)
• Meta-Learning with Self-Improving Momentum Target [72.98879709228981]
  We propose Self-improving Momentum Target (SiMT) to improve the performance of a meta-learner. SiMT generates the target model by adapting from the temporal ensemble of the meta-learner. We show that SiMT brings a significant performance gain when combined with a wide range of meta-learning methods.
  arXiv  Detail & Related papers  (2022-10-11T06:45:15Z)
• Model-Agnostic Multitask Fine-tuning for Few-shot Vision-Language Transfer Learning [59.38343286807997]
  We propose Model-Agnostic Multitask Fine-tuning (MAMF) for vision-language models on unseen tasks. Compared with model-agnostic meta-learning (MAML), MAMF discards the bi-level optimization and uses only first-order gradients. We show that MAMF consistently outperforms the classical fine-tuning method for few-shot transfer learning on five benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-09T17:26:53Z)
• Bootstrapped Meta-Learning [48.017607959109924]
  We propose an algorithm that tackles a challenging meta-optimisation problem by letting the meta-learner teach itself. The algorithm first bootstraps a target from the meta-learner, then optimises the meta-learner by minimising the distance to that target under a chosen (pseudo-)metric. We achieve a new state-of-the art for model-free agents on the Atari ALE benchmark, improve upon MAML in few-shot learning, and demonstrate how our approach opens up new possibilities.
  arXiv  Detail & Related papers  (2021-09-09T18:29:05Z)
• A contrastive rule for meta-learning [1.3124513975412255]
  Meta-learning algorithms leverage regularities that are present on a set of tasks to speed up and improve the performance of a subsidiary learning process. We present a gradient-based meta-learning algorithm based on equilibrium propagation. We establish theoretical bounds on its performance and present experiments on a set of standard benchmarks and neural network architectures.
  arXiv  Detail & Related papers  (2021-04-04T19:45:41Z)
• B-SMALL: A Bayesian Neural Network approach to Sparse Model-Agnostic Meta-Learning [2.9189409618561966]
  We propose a Bayesian neural network based MAML algorithm, which we refer to as the B-SMALL algorithm. We demonstrate the performance of B-MAML using classification and regression tasks, and highlight that training a sparsifying BNN using MAML indeed improves the parameter footprint of the model.
  arXiv  Detail & Related papers  (2021-01-01T09:19:48Z)
• Meta-Learning with Adaptive Hyperparameters [55.182841228303225]
  We focus on a complementary factor in MAML framework, inner-loop optimization (or fast adaptation) We propose a new weight update rule that greatly enhances the fast adaptation process.
  arXiv  Detail & Related papers  (2020-10-31T08:05:34Z)
• 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)

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.