paper-with-me

홈 › Papers

Robust Meta-learning with Noise via Eigen-Reptile

2021-01-01 · Dong Chen, Lingfei Wu, Siliang Tang, Fangli Xu, Juncheng Li, Chang Zong, Chilie Tan, Yueting Zhuang

Recent years have seen a surge of interest in meta-learning techniques for tackling the few-shot learning (FSL) problem. However, the meta-learner's initial model is prone to meta-overfit, as there are only a few available samples with sampling noise. Besides, when handling the data sampled with label noise for FSL, meta-learner could be extremely sensitive to label noise. To address these two challenges that FSL with sampling and label noise. In particular, we first cast the meta-overfitting problem (overfitting on sampling and label noise) as a gradient noise problem since few available samples cause meta-learner to overfit on existing examples (clean or corrupted) of an individual task at every gradient step. We present Eigen-Reptile (ER) that updates the meta-parameters with the main direction of historical task-specific parameters to alleviate gradient noise. Specifically, the main direction is computed by a special mechanism for the parameter's large size. Furthermore, to obtain a more accurate main direction for Eigen-Reptile in the presence of label noise, we propose Introspective Self-paced Learning (ISPL) that constructs a plurality of prior models to determine which sample should be abandoned. We have proved the effectiveness of Eigen-Reptile and ISPL, respectively, theoretically and experimentally. Moreover, our experiments on different tasks demonstrate that the proposed methods outperform or achieve highly competitive performance compared with the state-of-the-art methods with or without noisy labels.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot LearningMeta-Learning

Methods 이 논문이 사용한 방법론

ISPL Implicit Subspace Prior Learning, or ISPL, is a framework to approach dual-blind face restoration, with two major distinctions from previous restoration methods: 1)…

Similar Papers 제목 키워드 기반

Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile

2022-06-04 · Dong Chen, Lingfei Wu, Siliang Tang, Xiao Yun 외

Recent years have seen a surge of interest in meta-learning techniques for tackling the few-shot learning (FSL) problem. However, the meta-learner is prone to overfitting since there are only a few available samples, whi…

Few-Shot LearningMeta-Learning

EEG-Reptile: An Automatized Reptile-Based Meta-Learning Library for BCIs

2024-12-27 · Daniil A. Berdyshev, Artem M. Grachev, Sergei L. Shishkin, Bogdan L. Kozyrskiy

Meta-learning, i.e., "learning to learn", is a promising approach to enable efficient BCI classifier training with limited amounts of data. It can effectively use collections of in some way similar classification tasks, …

EEGFew-Shot LearningMeta-LearningTransfer Learning

Understanding Transfer Learning and Gradient-Based Meta-Learning Techniques

2023-10-09 · Mike Huisman, Aske Plaat, Jan N. van Rijn

Deep neural networks can yield good performance on various tasks but often require large amounts of data to train them. Meta-learning received considerable attention as one approach to improve the generalization of these…

DiversityMeta-LearningTransfer Learning

Meta-Learning for Few-Shot Named Entity Recognition

2021-08-01 · ACL (MetaNLP) 2021 8 · Cyprien de Lichy, Hadrien Glaude, William Campbell

Meta-learning has recently been proposed to learn models and algorithms that can generalize from a handful of examples. However, applications to structured prediction and textual tasks pose challenges for meta-learning a…

Language ModelingLanguage ModellingMeta-Learningnamed-entity-recognition+4

RAMario: Experimental Approach to Reptile Algorithm -- Reinforcement Learning for Mario

2023-05-16 · Sanyam Jain

This research paper presents an experimental approach to using the Reptile algorithm for reinforcement learning to train a neural network to play Super Mario Bros. We implement the Reptile algorithm using the Super Mario…

Few-Shot LearningMeta-Learningreinforcement-learningReinforcement Learning