Pseudo-Labeling Based Practical Semi-Supervised Meta-Training for Few-Shot Learning
Most existing few-shot learning (FSL) methods require a large amount of labeled data in meta-training, which is a major limit. To reduce the requirement of labels, a semi-supervised meta-training (SSMT) setting has been proposed for FSL, which includes only a few labeled samples and numbers of unlabeled samples in base classes. However, existing methods under this setting require class-aware sample selection from the unlabeled set, which violates the assumption of unlabeled set. In this paper, we propose a practical semi-supervised meta-training setting with truly unlabeled data to facilitate the applications of FSL in realistic scenarios. To better utilize both the labeled and truly unlabeled data, we propose a simple and effective meta-training framework, called pseudo-labeling based meta-learning (PLML). Firstly, we train a classifier via common semi-supervised learning (SSL) and use it to obtain the pseudo-labels of unlabeled data. Then we build few-shot tasks from labeled and pseudo-labeled data and design a novel finetuning method with feature smoothing and noise suppression to better learn the FSL model from noise labels. Surprisingly, through extensive experiments across two FSL datasets, we find that this simple meta-training framework effectively prevents the performance degradation of various FSL models under limited labeled data, and also significantly outperforms the state-of-the-art SSMT models. Besides, benefiting from meta-training, our method also improves two representative SSL algorithms as well.
Code (1)
Tasks
Few-Shot LearningMeta-LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Noise-injected Consistency Training and Entropy-constrained Pseudo Labeling for Semi-supervised Extractive Summarization
Labeling large amounts of extractive summarization data is often prohibitive expensive due to time, financial, and expertise constraints, which poses great challenges to incorporating summarization system in practical ap…
Extractive SummarizationPseudo-Representation Labeling Semi-Supervised Learning
In recent years, semi-supervised learning (SSL) has shown tremendous success in leveraging unlabeled data to improve the performance of deep learning models, which significantly reduces the demand for large amounts of la…
Data AugmentationRepresentation LearningMeta Propagation Networks for Graph Few-shot Semi-supervised Learning
Inspired by the extensive success of deep learning, graph neural networks (GNNs) have been proposed to learn expressive node representations and demonstrated promising performance in various graph learning tasks. However…
Graph LearningMeta-LearningSemi-supervised Contrastive Outlier removal for Pseudo Expectation Maximization (SCOPE)
Semi-supervised learning is the problem of training an accurate predictive model by combining a small labeled dataset with a presumably much larger unlabeled dataset. Many methods for semi-supervised deep learning have b…
Contrastive LearningSemiFed: Semi-supervised Federated Learning with Consistency and Pseudo-Labeling
Federated learning enables multiple clients, such as mobile phones and organizations, to collaboratively learn a shared model for prediction while protecting local data privacy. However, most recent research and applicat…
Data AugmentationFederated LearningPseudo Label