Task-Agnostic Meta-Learning for Few-shot Learning

2018-05-20 · Muhammad Abdullah Jamal, Guo-Jun Qi, Mubarak Shah

Meta-learning approaches have been proposed to tackle the few-shot learning problem.Typically, a meta-learner is trained on a variety of tasks in the hopes of being generalizable to new tasks. However, the generalizability on new tasks of a meta-learner could be fragile when it is over-trained on existing tasks during meta-training phase. In other words, the initial model of a meta-learner could be too biased towards existing tasks to adapt to new tasks, especially when only very few examples are available to update the model. To avoid a biased meta-learner and improve its generalizability, we propose a novel paradigm of Task-Agnostic Meta-Learning (TAML) algorithms. Specifically, we present an entropy-based approach that meta-learns an unbiased initial model with the largest uncertainty over the output labels by preventing it from over-performing in classification tasks. Alternatively, a more general inequality-minimization TAML is presented for more ubiquitous scenarios by directly minimizing the inequality of initial losses beyond the classification tasks wherever a suitable loss can be defined.Experiments on benchmarked datasets demonstrate that the proposed approaches outperform compared meta-learning algorithms in both few-shot classification and reinforcement learning tasks.

📄 PDF Abstract BibTeX arXiv:1805.07722

Code (0)

등록된 구현이 없습니다.

Tasks

Classification Few-Shot Learning General Classification Meta-Learning Reinforcement Learning

Attentive Task-Agnostic Meta-Learning for Few-Shot Text Classification

2019-05-01 · ICLR 2019 5 · Xiang Jiang, Mohammad Havaei, Gabriel Chartrand, Hassan Chouaib 외

Current deep learning based text classification methods are limited by their ability to achieve fast learning and generalization when the data is scarce. We address this problem by integrating a meta-learning procedure t…

Classification Few-Shot Text Classification General Classification Inductive Bias+8

Meta-Learning of Neural Architectures for Few-Shot Learning

2019-11-25 · CVPR 2020 6 · Thomas Elsken, Benedikt Staffler, Jan Hendrik Metzen, Frank Hutter

The recent progress in neural architecture search (NAS) has allowed scaling the automated design of neural architectures to real-world domains, such as object detection and semantic segmentation. However, one prerequisit…

Few-Shot Learning Meta-Learning Neural Architecture Search object-detection+2

Meta-Learning with Context-Agnostic Initialisations

2020-07-29 · Toby Perrett, Alessandro Masullo, Tilo Burghardt, Majid Mirmehdi 외

Meta-learning approaches have addressed few-shot problems by finding initialisations suited for fine-tuning to target tasks. Often there are additional properties within training data (which we refer to as context), not …

Meta-Learning