{"id":1445,"date":"2024-11-13T14:07:58","date_gmt":"2024-11-13T14:07:58","guid":{"rendered":"https:\/\/prg.inf.unibe.ch\/?page_id=1445"},"modified":"2024-11-13T16:11:02","modified_gmt":"2024-11-13T16:11:02","slug":"thesis-implementing-and-evaluating-kolmogorov-arnold-networks-in-graph-based-contexts","status":"publish","type":"page","link":"https:\/\/prg.inf.unibe.ch\/index.php\/education\/thesis-implementing-and-evaluating-kolmogorov-arnold-networks-in-graph-based-contexts\/","title":{"rendered":"thesis-Implementing-and-Evaluating-Kolmogorov-Arnold-Networks-in-Graph-Based-Contexts"},"content":{"rendered":"\n
<\/div>\n\n\n\n
<\/div>
\n
<\/div>\n

Implementing and Evaluating Kolmogorov-Arnold Networks in Graph-Based Contexts<\/h1>\n\n\n\n

Supervised by:<\/strong> Anthony Gillioz<\/p>\n\n\n\n

If you are interested in this topic or have further questions, do not hesitate to contact <\/a>anthony.gillioz@unibe.ch<\/a>.<\/p>\n\n\n\n

Context<\/strong><\/p>\n\n\n\n

This project aims to explore the application of Kolmogorov-Arnold Networks (KANs) in graph-based contexts.<\/p>\n\n\n\n

The Kolmogorov-Arnold Network (KAN) architecture is a relatively new and theoretically significant development in neural network research. Based on Kolmogorov\u2019s superposition theorem and extended by Arnold, KANs offer a robust framework for universal function approximation. Despite their theoretical promise, practical implementations of KANs, especially in graph-based contexts, are still underexplored. This project seeks to bridge that gap by demonstrating how KANs can be effectively applied to graph-based data, providing valuable insights into their potential across various domains.<\/p>\n\n\n\n

The project will involve researching existing implementations, reproducing a functional graph-based KAN, conducting experiments on graph datasets, and reporting the findings in a scientific paper.<\/p>\n\n\n\n

Goal(s)<\/strong><\/p>\n\n\n\n