M.Sc. Thesis: Graph Neural Networks’ Scalability
We are looking for a dedicated master’s student to join us in the Connected Intelligence Unit at RISE.
The Connected Intelligence Unit is part of RISE Computer Science in Kista. The current research focus is on devising intelligent autonomous systems for controlling and allocating resources in future computer and communication networks. Among the group's key technologies are Internet of Things (IoT) and Edge computing. The unit conducts projects together with industry and academic partners from Sweden and across the world.
Background and Purpose
Graph Neural Networks (GNN) have emerged as one of the main subfields of deep learning within the machine learning community. Among their advantages are their capability to process graph-structured data, their invariance to input and output dimension, and their capability to extract structural information from data. However, when deployed in practice, their diffusion processes in the GNNs’ message passing operations make it hard to obtain reproducible results on problem instances that scale well beyond the training data sizes.
This thesis aims at analyzing the factors affecting the scalability of GNNs to maintain adequate performance in network-sizes well beyond those seen in the training set. More specifically, taking two application use-cases from the networking domain and the combinatorial domain, the thesis student will evaluate the training factors and hyperparameters influencing the scalability of GNNs to maintain adequate performance in problem instance sizes well beyond those seen in the training dataset.
- Start Time: As soon as possible
- Scope: 30 hp
- Location: RISE Computer Science, Kista, Stockholm. Option to partially work remotely.
Who are you?
We expect you to have solid knowledge of machine learning theory, good programming skills and an interest in solving complex problems.
Welcome with your application!
To know more, please contact Daniel Pérez (firstname.lastname@example.org, tel 073 806 2917). Applications should include a brief personal letter, CV, and recent grades. Candidates are encouraged to send in their application as soon as possible but at the latest by the 15th of January 2023. Suitable applicants will be interviewed as soon as applications are received. We will not accept application via email.
Master thesis, Machine Learning, Graph Neural Networks, RISE, Stockholm
Student - examensarbete/praktik
2023-01-15Skicka in din ansökan