I am currently a PhD student at the University of Porto (base) and the University of Edinburgh. I am supervised by Prof. Dr. Viacheslav Borovitskiy and Prof. Dr. Pedro Ribeiro.
I am a member of Prof. Dr. Viacheslav Borovitskiy's research group, GLUEd. If you are interested in joining us, we occasionally have open positions!
My main research interests are geometric deep learning and uncertainty quantification. I am also interested in network science and topological deep learning.
Prior to starting my PhD, I was a Master's student at the University of Porto under the supervision of Prof. Dr. Pedro Ribeiro and Dr. Miguel E. P. Silva. I also gained research experience working with several distinguished researchers such as Prof. Dr. João Gama through research internships and participation in a summer school.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
University of PortoFaculty of Sciences - DCC&
University of EdinburghSchool of Informatics - IMLPh.D. StudentSep. 2025 - Present -
University of PortoFaculty of Sciences - DCCMSc. in Data ScienceSep. 2022 - Jul. 2024
-
CentraleSupélec, Paris-Saclay UniversitySummer SchoolJun. 2022 - Jul. 2022 -
University of PortoFaculty of Sciences - DCCBSc. in Computer ScienceSep. 2019 - Jul. 2022
Experience
-
INESC-TEC -- CRACSResearch AssitantSep. 2025 - Present -
DCC-FCUPResearch Assistant as Master's CandidateSep. 2023 - Jul. 2024 -
INESC-TEC -- LIAADResearch InternFeb. 2022 - Jan. 2023
-
INESC-TEC -- HumanISEResearch InternFeb. 2021 - Sep. 2021
News
Selected Publications (view all )
Studying and Improving Graph Neural Network-based Motif Estimation
Pedro C. Vieira#, Miguel E. P. Silva, Pedro Ribeiro (# corresponding author)
Pre-print 2025
We investigate how Message Passing Neural Networks (MPNNs) perform at estimating significance-profiles of synthetic and real-world graph datasets. We discover that despite the known theoretical limitations of MPNNs, surprisingly, they can make useful estimates, especially under a specialized multi-target regression problem formulation.
Studying and Improving Graph Neural Network-based Motif Estimation
Pedro C. Vieira#, Miguel E. P. Silva, Pedro Ribeiro (# corresponding author)
Pre-print 2025
We investigate how Message Passing Neural Networks (MPNNs) perform at estimating significance-profiles of synthetic and real-world graph datasets. We discover that despite the known theoretical limitations of MPNNs, surprisingly, they can make useful estimates, especially under a specialized multi-target regression problem formulation.