# Reconciling meta-learning and continual learning with online mixtures of tasks

arXiv: https://arxiv.org/abs/1812.06080 · HTML: https://mlsanity.com/paper/1812.06080/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2018.

## Built on by (most cited first, 3 of 3)

- [How Fine-Tuning Allows for Effective Meta-Learning](https://mlsanity.com/paper/2105.02221/) (2021)
- [Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy](https://mlsanity.com/paper/2406.16087/) (2024)
- [A Topology-aware Graph Coarsening Framework for Continual Graph Learning](https://mlsanity.com/paper/2401.03077/) (2024)

## Abstract (arXiv)

Learning-to-learn or meta-learning leverages data-driven inductive bias to increase the efficiency of learning on a novel task. This approach encounters difficulty when transfer is not advantageous, for instance, when tasks are considerably dissimilar or change over time. We use the connection between gradient-based meta-learning and hierarchical Bayes to propose a Dirichlet process mixture of hierarchical Bayesian models over the parameters of an arbitrary parametric model such as a neural network. In contrast to consolidating inductive biases into a single set of hyperparameters, our approach of task-dependent hyperparameter selection better handles latent distribution shift, as demonstrated on a set of evolving, image-based, few-shot learning benchmarks.