Meta Learning
Meta-learning, or "learning to learn," focuses on developing algorithms that can efficiently adapt to new tasks with limited data by leveraging prior experience from related tasks. Current research emphasizes improving the robustness and efficiency of meta-learning algorithms, particularly in low-resource settings, often employing model-agnostic meta-learning (MAML) and its variants, along with techniques like dynamic head networks and reinforcement learning for task selection. This field is significant because it addresses the limitations of traditional machine learning in data-scarce scenarios, with applications ranging from speech and image recognition to robotics and personalized medicine.
Papers
Meta-Learning in Audio and Speech Processing: An End to End Comprehensive Review
Athul Raimon, Shubha Masti, Shyam K Sateesh, Siyani Vengatagiri, Bhaskarjyoti Das
Meta-Learning on Augmented Gene Expression Profiles for Enhanced Lung Cancer Detection
Arya Hadizadeh Moghaddam, Mohsen Nayebi Kerdabadi, Cuncong Zhong, Zijun Yao
Meta-GCN: A Dynamically Weighted Loss Minimization Method for Dealing with the Data Imbalance in Graph Neural Networks
Mahdi Mohammadizadeh, Arash Mozhdehi, Yani Ioannou, Xin Wang
Meta-learning and Data Augmentation for Stress Testing Forecasting Models
Ricardo Inácio, Vitor Cerqueira, Marília Barandas, Carlos Soares
F-FOMAML: GNN-Enhanced Meta-Learning for Peak Period Demand Forecasting with Proxy Data
Zexing Xu, Linjun Zhang, Sitan Yang, Rasoul Etesami, Hanghang Tong, Huan Zhang, Jiawei Han
Meta-FL: A Novel Meta-Learning Framework for Optimizing Heterogeneous Model Aggregation in Federated Learning
Zahir Alsulaimawi