Toward Multimodal Model-Agnostic Meta-Learning

Abstract

Gradient-based meta-learners such as MAML are able to learn a meta-prior from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. One important limitation of such frameworks is that they seek a common initialization shared across the entire task distribution, substantially limiting the diversity of the task distributions that they are able to learn from. In this paper, we augment MAML with the capability to identify tasks sampled from a multimodal task distribution and adapt quickly through gradient updates. Specifically, we propose a multimodal MAML algorithm that is able to modulate its meta-learned prior according to the identified task, allowing faster adaptation. We evaluate the proposed model on a diverse set of problems including regression, few-shot image classification, and reinforcement learning. The results demonstrate the effectiveness of our model in modulating the meta-learned prior in response to the characteristics of tasks sampled from a multimodal distribution.

References in corpus (9)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Matching Networks for One Shot Learning
• A Simple Neural Attentive Meta-Learner
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• RL${}^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
• Learning to reinforcement learn
• Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
• Attentive Recurrent Comparators

Cited by in corpus (8)

• GeneraLight: Improving Environment Generalization of Traffic Signal Control via Meta Reinforcement Learning
• Automated Relational Meta-learning
• Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning
• Learning to Synthesize Programs as Interpretable and Generalizable Policies
• Compositional ADAM: An Adaptive Compositional Solver
• Weighted Meta-Learning
• Model-Agnostic Learning to Meta-Learn
• Connecting Context-specific Adaptation in Humans to Meta-learning