Continuous Meta-Learning without Tasks
arXiv:1912.08866
Abstract
Meta-learning is a promising strategy for learning to efficiently learn within new tasks, using data gathered from a distribution of tasks. However, the meta-learning literature thus far has focused on the task segmented setting, where at train-time, offline data is assumed to be split according to the underlying task, and at test-time, the algorithms are optimized to learn in a single task. In this work, we enable the application of generic meta-learning algorithms to settings where this task segmentation is unavailable, such as continual online learning with a time-varying task. We present meta-learning via online changepoint analysis (MOCA), an approach which augments a meta-learning algorithm with a differentiable Bayesian changepoint detection scheme. The framework allows both training and testing directly on time series data without segmenting it into discrete tasks. We demonstrate the utility of this approach on a nonlinear meta-regression benchmark as well as two meta-image-classification benchmarks.
arXiv commentNeurIPS 2020
References in corpus (13)
- Overcoming catastrophic forgetting in neural networks
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- Theoretical Models of Learning to Learn
- Bayesian Online Changepoint Detection
- Learning to reinforcement learn
- Task Agnostic Continual Learning via Meta Learning
- Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL
- Recurrent switching linear dynamical systems
- Thompson Sampling in Switching Environments with Bayesian Online Change Point Detection
- Spatio-temporal Bayesian On-line Changepoint Detection with Model Selection
- Meta-learning with Stochastic Linear Bandits
- Fair Meta-Learning: Learning How to Learn Fairly