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
Few-shot Bioacoustic Event Detection with Machine Learning Methods
Leah Chowenhill, Gaurav Satyanath, Shubhranshu Singh, Madhav Mahendra Wagh
Longitudinal Prediction of Postnatal Brain Magnetic Resonance Images via a Metamorphic Generative Adversarial Network
Yunzhi Huang, Sahar Ahmad, Luyi Han, Shuai Wang, Zhengwang Wu, Weili Lin, Gang Li, Li Wang, Pew-Thian Yap
MetaGL: Evaluation-Free Selection of Graph Learning Models via Meta-Learning
Namyong Park, Ryan Rossi, Nesreen Ahmed, Christos Faloutsos
EEML: Ensemble Embedded Meta-learning
Geng Li, Boyuan Ren, Hongzhi Wang
Provable Generalization of Overparameterized Meta-learning Trained with SGD
Yu Huang, Yingbin Liang, Longbo Huang