A Brief Summary of Interactions Between Meta-Learning and Self-Supervised Learning
원문 초록
This paper briefly reviews the connections between meta-learning and self-supervised learning. Meta-learning can be applied to improve model generalization capability and to construct general AI algorithms. Self-supervised learning utilizes self-supervision from original data and extracts higher-level generalizable features through unsupervised pre-training or optimization of contrastive loss objectives. In self-supervised learning, data augmentation techniques are widely applied and data labels are not required since pseudo labels can be estimated from trained models on similar tasks. Meta-learning aims to adapt trained deep models to solve diverse tasks and to develop general AI algorithms. We review the associations of meta-learning with both generative and contrastive self-supervised learning models. Unlabeled data from multiple sources can be jointly considered even when data sources are vastly different. We show that an integration of meta-learning and self-supervised learning models can best contribute to the improvement of model generalization capability. Self-supervised learning guided by meta-learner and general meta-learning algorithms under self-supervision are both examples of possible combinations.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
scSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell Data
Iceberg: Enhancing HLS Modeling with Synthetic Data
Speech Quality Assessment Model Based on Mixture of Experts: System-Level Performance Enhancement and Utterance-Level Challenge Analysis
Self-supervised Feature Extraction for Enhanced Ball Detection on Soccer Robots
Exploring Non-contrastive Self-supervised Representation Learning for Image-based Profiling
Graph Neural Networks in Modern AI-aided Drug Discovery
토론
이 논문과 연결된 포럼 글이 아직 없습니다.