A meta-learning approach for graph representation learning in multi-task settings

D Buffelli, F Vandin - arXiv preprint arXiv:2012.06755, 2020 - arxiv.org
Graph Neural Networks (GNNs) are a framework for graph representation learning, where a
model learns to generate low dimensional node embeddings that encapsulate structural and …

Graph representation learning for multi-task settings: a meta-learning approach

D Buffelli, F Vandin - 2022 International Joint Conference on …, 2022 - ieeexplore.ieee.org
Graph Neural Networks (GNNs) have become the state-of-the-art method for many
applications on graph structured data. GNNs are a model for graph representation learning …

Can i see an example? active learning the long tail of attributes and relations

TL Hayes, M Nickel, C Kanan, L Denoyer… - arXiv preprint arXiv …, 2022 - arxiv.org
There has been significant progress in creating machine learning models that identify
objects in scenes along with their associated attributes and relationships; however, there is …

Improving the Effectiveness of Graph Neural Networks in Practical Scenarios

D Buffelli - 2023 - research.unipd.it
In the past decade, deep learning has given new life to the field of artificial intelligence,
providing many breakthroughs in areas like computer vision, natural language processing …