cv

Graduate teaching assistant

Halmstad University

Teaching assistant in the following courses: Introduction to Data Science, Machine Leanring, Learning Systems.

Undergraduate research assistant

CosyncLab, Rome

Research assistant during the Master's thesis. Working on the ERC HANDmade Project.

Ph.D.

Halmstad University

• Meta-learning for enhanced generalizability in machine learning models

M.Sc

Padua University

• ICT for Internet and Multimedia, curricula Life and Health

B.Sc

Padua University

• Information Engineering

Personalized Federated Learning with Contextual Modulation and Meta-Learning.

SIAM Conference on Data Mining (SDM)

Anna Vettoruzzo, Mohamed-Rafik Bouguelia, and Thorsteinn Rögnvaldsson.

Meta-Learning for Efficient Unsupervised Domain Adaptation

Neurocomputing

Anna Vettoruzzo, Mohamed-Rafik Bouguelia, and Thorsteinn Rögnvaldsson.

Multimodal Meta-Learning through Meta-Learned Task Representations.

Neural Computing and Applications

Anna Vettoruzzo, Mohamed-Rafik Bouguelia, and Thorsteinn Rögnvaldsson.

Advances and Challenges in Meta-Learning: A Technical Review.

IEEE Transactions on Pattern Analysis & Machine Intelligence

Anna Vettoruzzo, Mohamed-Rafik Bouguelia, Joaquin Vanschoren, Thorsteinn Rögnvaldsson, and K. C. Santosh.

Learning to Learn without Forgetting using Attention.

The Third Conference on Lifelong Learning Agents (CoLLAs)

Anna Vettoruzzo, Joaquin Vanschoren, Mohamed-Rafik Bouguelia, and Thorsteinn Rögnvaldsson.

Efficient Few-Shot Human Activity Recognition via Meta-Learning and Data Augmentation.

In review.

Anna Vettoruzzo, Mohamed-Rafik Bouguelia, and Thorsteinn Rögnvaldsson.

Unsupervised meta-learning via in-context learning.

In review.

Anna Vettoruzzo, Lorenzo Braccaioli, Joaquin Vanschoren, Marlena Nowaczyk.

Meta-Learning from Multimodal Task Distributions Using Multiple Sets of Meta-Parameters.

International Joint Conference Neural Networks (IJCNN)

Anna Vettoruzzo, Mohamed-Rafik Bouguelia, and Thorsteinn Rögnvaldsson.

Meta-learning for continual learning

We propose to apply meta-learning to solve CL problems by meta-learning the weights and the hyperparameters of a neural network.