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

October 4, 2022

Uncertainty-Aware Meta-Learning for Multimodal Task Distributions
Cesar Almecija, Apoorva Sharma, Navid Azizan
Meta Learning Uncertainty Aware Multimodal Task

October 3, 2022

Learning with Limited Samples -- Meta-Learning and Applications to Communication Systems
Lisha Chen, Sharu Theresa Jose, Ivana Nikoloska, Sangwoo Park, Tianyi Chen, Osvaldo Simeone
Deep Learning LeArning Abstract Deep Learning Model Financial Application Meta Learning Joint Learning Communication System Limited Sample Shot Meta Learning

September 27, 2022

Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning
Xingping Dong, Jianbing Shen, Ling Shao
Pseudo Label Meta Learning Pseudo Labeling Supervised Approach

September 26, 2022

TaskMix: Data Augmentation for Meta-Learning of Spoken Intent Understanding
Surya Kant Sahu
Data Augmentation Multi Task Learning Meta Learning Human Machine Automatic Speech Recognition Hypothesis Task Diversity

September 24, 2022

Graph Neural Network Expressivity and Meta-Learning for Molecular Property Regression
Haitz Sáez de Ocáriz Borde, Federico Barbero
Shot Learning Meta Learning Regression Task GNN Model Molecular Property Expressive Graph Neural Network

September 23, 2022

Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-Learning
Boris Ivanovic, James Harrison, Marco Pavone
Meta Learning Autonomous System Online Adaptation Behavior Prediction Bayesian Regression Speech Envelope

September 22, 2022

An Investigation of the Bias-Variance Tradeoff in Meta-Gradients
Risto Vuorio, Jacob Beck, Shimon Whiteson, Jakob Foerster, Gregory Farquhar
Reinforcement Learning Meta Learning Bias Variance Meta Gradient

September 21, 2022

Consecutive Knowledge Meta-Adaptation Learning for Unsupervised Medical Diagnosis
Yumin Zhang, Yawen Hou, Xiuyi Chen, Hongyuan Yu, Long Xia
Domain Adaptation Meta Learning Lesion Segmentation Lesion Wise Metric Unsupervised Medical

September 20, 2022

Meta-Learning for Adaptive Filters with Higher-Order Frequency Dependencies
Junkai Wu, Jonah Casebeer, Nicholas J. Bryan, Paris Smaragdis
Meta Learning Adaptive Filter Echo Cancellation Frequency Perspective

September 19, 2022

Meta-Reinforcement Learning for Adaptive Control of Second Order Systems
Daniel G. McClement, Nathan P. Lawrence, Michael G. Forbes, Philip D. Loewen, Johan U. Backström, R. Bhushan Gopaluni
Meta Learning Second Order Meta Reinforcement Learning Adaptive Control Model Free Policy Generalizable Controller

September 14, 2022

Meta-RegGNN: Predicting Verbal and Full-Scale Intelligence Scores using Graph Neural Networks and Meta-Learning
Imen Jegham, Islem Rekik
Graph Neural Network Meta Learning Brain Network Structural Connectome Functional Connectome Verbal Communication Meta Training Stage Intelligence Test

September 12, 2022

Online Continual Learning via the Meta-learning Update with Multi-scale Knowledge Distillation and Data Augmentation
Ya-nan Han, Jian-wei Liu
Knowledge Distillation Data Augmentation Continual LEArning Catastrophic Forgetting Meta Learning Online Continual Learning

September 10, 2022

Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification
Tianyi Lei, Honghui Hu, Qiaoyang Luo, Dezhong Peng, Xu Wang
Meta Learning Shot Text Classification Gradient Similarity Optimization Based Meta Learning

September 1, 2022

The Neural Process Family: Survey, Applications and Perspectives
Saurav Jha, Dong Gong, Xuesong Wang, Richard E. Turner, Lina Yao
Timely Survey Financial Application Gaussian Process Meta Learning Synthesized View Neural Process

August 31, 2022

NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline results
Dustin Carrión-Ojeda, Hong Chen, Adrian El Baz, Sergio Escalera, Chaoyu Guan, Isabelle Guyon, Ihsan Ullah, Xin Wang, Wenwu Zhu
Product Design Meta Learning Baseline Result Competition Platform Image Classification Datasets Meta Dataset Domain Few Shot

August 24, 2022

A model-based approach to meta-Reinforcement Learning: Transformers and tree search
Brieuc Pinon, Jean-Charles Delvenne, Raphaël Jungers
Transformer Megatron Decepticons Meta Learning Model Based Model Free Meta Reinforcement Learning Tree Search Meta Rl Algorithm

August 19, 2022

Meta Learning for High-dimensional Ising Model Selection Using $\ell_1$-regularized Logistic Regression
Huiming Xie, Jean Honorio
Generative Model Meta Learning Sample Complexity Logistic Regression Ising Model

August 18, 2022

Meta-Learning Online Control for Linear Dynamical Systems
Deepan Muthirayan, Dileep Kalathil, Pramod P. Khargonekar
Meta Learning Linear Dynamical System Online Control Algorithm Achievable Regret

August 17, 2022

Meta Learning

Papers

Uncertainty-Aware Meta-Learning for Multimodal Task Distributions

Learning with Limited Samples -- Meta-Learning and Applications to Communication Systems

Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning

TaskMix: Data Augmentation for Meta-Learning of Spoken Intent Understanding

Graph Neural Network Expressivity and Meta-Learning for Molecular Property Regression

Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-Learning

An Investigation of the Bias-Variance Tradeoff in Meta-Gradients

Consecutive Knowledge Meta-Adaptation Learning for Unsupervised Medical Diagnosis

Meta-Learning for Adaptive Filters with Higher-Order Frequency Dependencies

Meta-Reinforcement Learning for Adaptive Control of Second Order Systems

Meta-RegGNN: Predicting Verbal and Full-Scale Intelligence Scores using Graph Neural Networks and Meta-Learning

Online Continual Learning via the Meta-learning Update with Multi-scale Knowledge Distillation and Data Augmentation

Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification

The Neural Process Family: Survey, Applications and Perspectives

NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline results

A model-based approach to meta-Reinforcement Learning: Transformers and tree search

Meta Learning for High-dimensional Ising Model Selection Using $\ell_1$-regularized Logistic Regression

Meta-Learning Online Control for Linear Dynamical Systems

Gradient-Based Meta-Learning Using Uncertainty to Weigh Loss for Few-Shot Learning

Maximising the Utility of Validation Sets for Imbalanced Noisy-label Meta-learning