Meta-Learning: A Survey

2018/10/08 by Joaquin Vanschoren, Vanschoren, Joaquin · 197 citations
Computer Science · Engineering · Mathematics · Psychology · #Artificial intelligence #Computer science #Deep learning #Domain Adaptation and Few-Shot Learning #Engineering #FOS: Computer and information sciences #Field (mathematics) #Learning design #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Machine Learning and Data Classification #Machine learning #Mathematics education #Meta learning (computer science) #Psychology #Range (aeronautics) #Systems engineering #Task (project management) #cs.LG #stat.ML

paper · pdf · open access · doi:10.48550/arxiv.1810.03548

published in TU/e Research Portal

arxiv created 2018/10/08 · openalex publication_date 2018/10/08 · arxiv updated 2018/10/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Meta-learning, or learning to learn, is the science of systematically observing how different machine learning approaches perform on a wide range of learning tasks, and then learning from this experience, or meta-data, to learn new tasks much faster than otherwise possible. Not only does this dramatically speed up and improve the design of machine learning pipelines or neural architectures, it also allows us to replace hand-engineered algorithms with novel approaches learned in a data-driven way. In this chapter, we provide an overview of the state of the art in this fascinating and continuously evolving field.

Cited by

• MetaRank: Task-Aware Metric Selection for Model Transferability Estimation
• Structured Matrix Scaling for Multi-Class Calibration
• Archaeological Classification of Small Datasets Using Meta- and Transfer Learning Methods: A Case Study on Hittite Stele Fragments
• Elements of Active Continuous Learning and Uncertainty Self-Awareness: a Narrow Implementation for Face and Facial Expression Recognition
• A Survey of Inductive Reasoning for Large Language Models
• Automated Machine Learning for Unsupervised Tabular Tasks
• Opt-ICL at LeWiDi-2025: Maximizing In-Context Signal from Rater Examples via Meta-Learning
• Pre-Hoc Predictions in AutoML: Leveraging LLMs to Enhance Model Selection and Benchmarking for Tabular datasets
• Dynamic Meta-Learning for Adaptive XGBoost-Neural Ensembles
• InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarios
• Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy
• MetaLLMix : An XAI Aided LLM-Meta-learning Based Approach for Hyper-parameters Optimization
• Robust and Adaptive Spectral Method for Representation Multi-Task Learning with Contamination
• M3OOD: Automatic Selection of Multimodal OOD Detectors
• Exploring Strategies for Personalized Radiation Therapy: Part III Identifying genetic determinants for Radiation Response with Meta Learning
• ICM-Fusion: In-Context Meta-Optimized LoRA Fusion for Multi-Task Adaptation
• Deep Generative Models in Condition and Structural Health Monitoring: Opportunities, Limitations and Future Outlook
• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
• Amazon SageMaker Autopilot: a white box AutoML solution at scale
• Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD
• Beyond Categorical Label Representations for Image Classification
• ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback
• Towards Dynamic Feature Selection with Attention to Assist Banking Customers in Establishing a New Business
• Prior-Enhanced Few-Shot Segmentation with Meta-Prototypes
• MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment
• Low-Cost Outdoor Air Quality Monitoring and Sensor Calibration: A Survey and Critical Analysis
• Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
• Efficient AutoML Pipeline Search with Matrix and Tensor Factorization
• Data Augmentation for Object Detection via Differentiable Neural Rendering
• When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey
• An Extensive Experimental Evaluation of Automated Machine Learning Methods for Recommending Classification Algorithms (Extended Version)
• Automated Machine Learning Techniques for Data Streams
• Hyperparameter Optimization via Interacting with Probabilistic Circuits
• Lesion2Vec: Deep Metric Learning for Few-Shot Multiple Lesions Recognition in Wireless Capsule Endoscopy Video
• PREMISE: Matching-based Prediction for Accurate Review Recommendation
• MetaCI: Meta-Learning for Causal Inference in a Heterogeneous Population
• Predicting Water Temperature Dynamics of Unmonitored Lakes With Meta‐Transfer Learning
• Magnification Generalization For Histopathology Image Embedding
• A critique of pure learning and what artificial neural networks can learn from animal brains
• Fast-adapting and Privacy-preserving Federated Recommender System
• The AI Cosmologist I: An Agentic System for Automated Data Analysis

Related

• Meta-Learning and representation learner: A short theoretical note
• Advances and Challenges in Meta-Learning: A Technical Review
• A Comprehensive Overview and Survey of Recent Advances in Meta-Learning
• Meta-Learning in Neural Networks: A Survey
• Meta Learning for Natural Language Processing: A Survey