LGMLFeb 11, 2020

Meta-Learning across Meta-Tasks for Few-Shot Learning

arXiv:2002.04274v411 citations
AI Analysis

This addresses few-shot learning for AI systems needing rapid adaptation with limited data, but it is incremental as it builds on existing meta-learning frameworks.

The paper tackled the problem of few-shot learning by proposing to exploit relationships between meta-tasks during meta-learning, introducing meta-domain adaptation and meta-knowledge distillation objectives to improve robustness to domain gaps and poorly sampled few-shots. However, the paper was withdrawn due to mistakes in the experiments, so no concrete results are reported.

Existing meta-learning based few-shot learning (FSL) methods typically adopt an episodic training strategy whereby each episode contains a meta-task. Across episodes, these tasks are sampled randomly and their relationships are ignored. In this paper, we argue that the inter-meta-task relationships should be exploited and those tasks are sampled strategically to assist in meta-learning. Specifically, we consider the relationships defined over two types of meta-task pairs and propose different strategies to exploit them. (1) Two meta-tasks with disjoint sets of classes: this pair is interesting because it is reminiscent of the relationship between the source seen classes and target unseen classes, featured with domain gap caused by class differences. A novel learning objective termed meta-domain adaptation (MDA) is proposed to make the meta-learned model more robust to the domain gap. (2) Two meta-tasks with identical sets of classes: this pair is useful because it can be employed to learn models that are robust against poorly sampled few-shots. To that end, a novel meta-knowledge distillation (MKD) objective is formulated. There are some mistakes in the experiments. We thus choose to withdraw this paper.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes