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
What Matters For Meta-Learning Vision Regression Tasks?
Ning Gao, Hanna Ziesche, Ngo Anh Vien, Michael Volpp, Gerhard Neumann
MetaCon: Unified Predictive Segments System with Trillion Concept Meta-Learning
Keqian Li, Yifan Hu, Logan Palanisamy, Lisa Jones, Akshay Gupta, Jason Grigsby, Ili Selinger, Matt Gillingham, Fei Tan
SuperCone: Unified User Segmentation over Heterogeneous Experts via Concept Meta-learning
Keqian Li, Yifan Hu