Welcome

I am a PhD student in the machine learning group at the Department of Informatics at the University of Bergen. My main fields of interest are topological data analysis (TDA) and geometric deep learning.

You can find some of my recent activities below. If you have any questions or want to collaborate with me, feel free to contact me.

Code

Here are some of my public GitHub repositories.

Traffic Graphs • Predicting the next hour’s traffic volumes in western Norway using graph neural networks. With examples showing how graph convolution leverages the spatial information of traffic data to perform better than the fully connected baseline model.

3D Point Cloud Classification • Various experiments on 3D point cloud classification (ModelNet40 dataset) using set and graph neural network architectures.

Group Equivariant CNN • An implementation of group equivariant convolutional networks (introduced by Cohen, T. – 2016) in PyTorch. Comparing the performance of group equivariant convolution against a more naïve approach (group average) and standard convolution on weather prediction from stereo images.

SimCLR • A PyTorch implementation of the self-supervised contrastive learning method SimCLR (A Simple Framework for Contrastive Learning of Visual Representations) introduced in Chen, T. et al. – 2020.

ArcFace and Triplet Network • PyTorch implementation of Triplet Margin Loss with various online mining strategies (see Xuan, H. et al. – 2019) to improve training, and the Angular Margin Loss from ArcFace (Deng, J. et al. – 2018)

Q-læring • An introductory tutorial to tabular Q-learning with a maze solving agent. Written in Norwegian aimed at students new to programming.

Codenames Spymaster • Generate clues for the boardgame Codenames using pre-trained word embeddings and a score function inspired by contrastive learning methods.

SLEDE8 Disassembler • A disassembler for the language SLEDE8 invented by PST (Norwegian Police Security Service) for one of their Christmas CTFs.

Ordl • Wordl clone for your terminal. To play while waiting for your models to finish training.

Papers

Papers that I have been part of.

Core Bifiltration (preprint)

2024 • Nello Blaser, Morten Brun, Odin Hoff Gardaa, Lars M. Salbu

arXivcode

TopoX: A Suite of Python Packages for Machine Learning on Topological Domains

2024 • Mustafa Hajij, Mathilde Papillon, Florian Frantzen, Jens Agerberg, Ibrahem AlJabea, Ruben Ballester, Claudio Battiloro, Guillermo Bernárdez, Tolga Birdal, Aiden Brent, Peter Chin, Sergio Escalera, Simone Fiorellino, Odin Hoff Gardaa, Gurusankar Gopalakrishnan, Devendra Govil, Josef Hoppe, Maneel Reddy Karri, Jude Khouja, Manuel Lecha, Neal Livesay, Jan Meißner, Soham Mukherjee, Alexander Nikitin, Theodore Papamarkou, Jaro Prílepok, Karthikeyan Natesan Ramamurthy, Paul Rosen, Aldo Guzmán-Sáenz, Alessandro Salatiello, Shreyas N. Samaga, Simone Scardapane, Michael T. Schaub, Luca Scofano, Indro Spinelli, Lev Telyatnikov, Quang Truong, Robin Walters, Maosheng Yang, Olga Zaghen, Ghada Zamzmi, Ali Zia, Nina Miolane

arXivcode

ICML 2023 Topological Deep Learning Challenge : Design and Results

2023 • Mathilde Papillon, Mustafa Hajij, Helen Jenne, Johan Mathe, Audun Myers, Theodore Papamarkou, Tolga Birdal, Tamal Dey, Tim Doster, Tegan Emerson, Gurusankar Gopalakrishnan, Devendra Govil, Aldo Guzmán-Sáenz, Henry Kvinge, Neal Livesay, Soham Mukherjee, Shreyas N. Samaga, Karthikeyan Natesan Ramamurthy, Maneel Reddy Karri, Paul Rosen, Sophia Sanborn, Robin Walters, Jens Agerberg, Sadrodin Barikbin, Claudio Battiloro, Gleb Bazhenov, Guillermo Bernardez, Aiden Brent, Sergio Escalera, Simone Fiorellino, Dmitrii Gavrilev, Mohammed Hassanin, Paul Häusner, Odin Hoff Gardaa, Abdelwahed Khamis, Manuel Lecha, German Magai, Tatiana Malygina, Rubén Ballester, Kalyan Nadimpalli, Alexander Nikitin, Abraham Rabinowitz, Alessandro Salatiello, Simone Scardapane, Luca Scofano, Suraj Singh, Jens Sjölund, Pavel Snopov, Indro Spinelli, Lev Telyatnikov, Lucia Testa, Maosheng Yang, Yixiao Yue, Olga Zaghen, Ali Zia, Nina Miolane

arXivcode

Miscellaneous

AI in Healthcare: Are We Jumping the Gun? • An essay I wrote about some of the ethical issues related to the application of AI in health care.

The topology of flight paths • Promo slides for a master’s thesis project I have proposed where we study flight traffic data using topological data analysis.

Multicomplexes over a field (Slides) • Slides for my presentation on multicomplexes given at the Topology seminar, November 2022 at the University of Bergen mathematics department.

Master’s Thesis • My master’s thesis on multicomplexes over a field and their associated spectral sequences. Supervisor: Markus Szymik.

Bachelor’s Thesis • My bachelor’s thesis about 2-dimensional topological quantum field theories and their connection to Frobenius algebras, closely following Joachim Kock’s book. Supervisor: Claudia Scheimbauer.