ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learning

Abstract

Optimization-based meta-learning typically assumes tasks are sampled from a single distribution - an assumption oversimplifies and limits the diversity of tasks that meta-learning can model. Handling tasks from multiple different distributions is challenging for meta-learning due to a so-called task ambiguity issue. This paper proposes a novel method, ST-MAML, that empowers model-agnostic meta-learning (MAML) to learn from multiple task distributions. ST-MAML encodes tasks using a stochastic neural network module, that summarizes every task with a stochastic representation. The proposed Stochastic Task (ST) strategy allows a meta-model to get tailored for the current task and enables us to learn a distribution of solutions for an ambiguous task. ST-MAML also propagates the task representation to revise the encoding of input variables. Empirically, we demonstrate that ST-MAML matches or outperforms the state-of-the-art on two few-shot image classification tasks, one curve regression benchmark, one image completion problem, and a real-world temperature prediction application. To the best of authors' knowledge, this is the first time optimization-based meta-learning method being applied on a large-scale real-world task.

References in corpus (17)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• The information bottleneck method
• Matching Networks for One Shot Learning
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Meta-Learning for Semi-Supervised Few-Shot Classification
• Meta-Learning with Implicit Gradients
• TADAM: Task dependent adaptive metric for improved few-shot learning
• A Closer Look at Few-shot Classification
• Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
• Hierarchically Structured Meta-learning
• Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation
• The Functional Neural Process
• Probabilistic Model-Agnostic Meta-Learning
• Automated Relational Meta-learning
• Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables
• Meta-Learning with Adaptive Hyperparameters
• Information Theoretic Meta Learning with Gaussian Processes