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
Deep domain adaptation for polyphonic melody extraction
Kavya Ranjan Saxena, Vipul Arora
MetaASSIST: Robust Dialogue State Tracking with Meta Learning
Fanghua Ye, Xi Wang, Jie Huang, Shenghui Li, Samuel Stern, Emine Yilmaz
Meta-learning Pathologies from Radiology Reports using Variance Aware Prototypical Networks
Arijit Sehanobish, Kawshik Kannan, Nabila Abraham, Anasuya Das, Benjamin Odry
Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components
Soumyabrata Pal, Prateek Varshney, Prateek Jain, Abhradeep Guha Thakurta, Gagan Madan, Gaurav Aggarwal, Pradeep Shenoy, Gaurav Srivastava
Missing Modality meets Meta Sampling (M3S): An Efficient Universal Approach for Multimodal Sentiment Analysis with Missing Modality
Haozhe Chi, Minghua Yang, Junhao Zhu, Guanhong Wang, Gaoang Wang