Online gradient-based mixtures for transfer modulation in meta-learning

By Ghassen Jerfel, Erin Grant, T. Griffiths, Katherine A. Heller. 2018

12 citations recorded by the source corpus.

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 mutually beneficial, for instance, when tasks are sufficiently dissimilar or change over time. Here, we use the connection between gradient-based meta-learning and hierarchical Bayes (Grant et al., 2018) to propose a mixture of hierarchical Bayesian models over the parameters of an arbitrary function approximator such as a neural network. Generalizing the model-agnostic meta-learning (MAML) algorithm (Finn et al., 2017), we present a stochastic expectation maximization procedure to jointly estimate parameter initializations for gradient descent as well as a latent assignment of tasks to initializations. This approach better captures the diversity of training tasks as opposed to consolidating inductive biases into a single set of hyperparameters. Our experiments demonstrate better generalization performance on the standard miniImageNet benchmark for 1-shot classification. We further derive a novel and scalable non-parametric variant of our method that captures the evolution of a task distribution over time as demonstrated on a set of few-shot regression tasks.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Adaptive Gradient-Based Meta-Learning Methods (2019, methodology): “(2017) and has been widely used in practice (Li et al., 2017; Al-Shedivat et al., 2018; Nichol et al., 2018; Jerfel et al., 2018).”
Continuous Meta-Learning without Tasks (2019, methodology): “Previous work (Nagabandi et al., 2019b; Jerfel et al., 2019; Knoblauch & Damoulas, 2018) has addressed the case in which tasks reoccur in both meta-learning and the BOCPD framework, and thus knowledge (in the form of a posterior estimate) may be re-used.”
Provable Guarantees for Gradient-Based Meta-Learning (2019, background): “A great deal of empirical work has studied and extended this approach (Li et al., 2017; Grant et al., 2018; Nichol et al., 2018; Jerfel et al., 2018); in particular, Nichol et al. (2018) develop Reptile, a simple yet equally effective ﬁrst-order simpliﬁcation of MAML for which our analysis shows…”
Multi-Step Model-Agnostic Meta-Learning: Convergence and Improved Algorithms (2020, background): “Many follow-up studies (Grant et al., 2018; Finn et al., 2019; Jerfel et al., 2018; Finn and Levine, 2017; Finn et al., 2018; Mi et al., 2019; Liu et al., 2019; Rothfuss et al., 2018; Foerster et al., 2018; Fallah et al., 2019; Collins et al., 2020; Fallah et al., 2020) have extended MAML from diffe”
Continual Adaptation for Efficient Machine Communication (2019, background): “There is a deep theoretical connection between the hierarchical Bayesian framework presented in the previous section and recent deep learning approaches to multi-task learning (Nagabandi et al., 2018; Grant et al., 2018; Jerfel et al., 2018).”