Klasifikacija grafova korištenjem metoda strojnog učenja

master's thesis

• Title (english): Graph classification using machine learning techniques
• Author: Ana Čačić
• Mentor: Lana Horvat Dmitrović (mentor)
• Committee member: Lana Horvat Dmitrović (predsjednik povjerenstva)
• Committee member: Andrea Aglić Aljinović (član povjerenstva)
• Committee member: Josipa Pina Milišić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-09-19, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Područje strojnog učenja temeljeno na grafovima je u posljednje vrijeme privuklo značajnu pozornost zbog svojeg potencijala rješavanja složenih realnih problema koji se mogu modelirati pomoću strukture grafa. Ovaj rad proučava problem klasifikacije grafova stvarajući novi skup podataka, koji predstavlja cestovne mreže europskih gradova, s ciljem da se modele istrenira klasificirati gradove u njihovu odgovarajuću državu. Problemu se pristupilo koristeći različite neuronske mreže grafova (GNN) kao što su GAT i GIN. Iako ne donosi finalni zaključak o izvedivosti ovog zadatka, ovaj rad služi kao početni korak u daljnjem istraživanju ovog problema.

Abstract (english)

The field of graph-based machine learning has recently gained a significant amount of attention due to its potential to solve complex real-world problems that can be modeled as graphs. This thesis delves into the problem of graph classification by creating a unique dataset that represents road networks across European cities and setting an objective to train models to classify these cities into their respective countries. This task was approached by using different graph neural networks (GNN), such as GAT and GIN. Although this thesis yields no definite conclusion regarding the feasibility of this task, it serves as an initial step in further research of this challenge.

• Keywords: klasifikacija grafova; graf neuronske mreže; GNN; GAT; GIN
• Keywords (english): graph classification; graph neural networks; GNN; GAT; GIN
• Language: english
• URN:NBN: urn:nbn:hr:168:349963
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-10-11 08:37:16