Machine Learning for Graphs

Machine Learning for Graphs

Internship Description

We have numerous projects where we work networks or graphs of various kinds, biological ones in particular. Networks can be undirected, directed with or without signs, discrete or continuous. For publications see google scholar (https://scholar.google.com/citations?hl=sv&user=_DUppAgAAAAJ&view_op=list_works&so rtby=pubdate).

Challenges and sub-projects include:

-          How to compare 2 and several networks, review, benchmark current methods, invent new efficient algorithms for network comparison

-          Analyze networks embedded in hyperbolic space

-          Review, benchmark current methods for embedding networks into an ML framework

-          Generative modeling of networks constrained by correlational information from data-sets

-          Partially overlapping networks, analyze their putative alignment, construction of multi-layer networks from several partially overlapping graphs.

-          Search and propagation in multi-layer networks

Alignment of several but different real protein interaction networks

Deliverables/Expectations

Individual projects will be tailored and narrowly designed from the above palette according to interest of the student, technical proficiency, and level of study. We expect you (a) to bring enthusiasm, creativity, and hard work, (b) give lab seminars on your work, and (c) produce a final written report. In return this facilitates your critical thinking, presentations skills, and scientific writing. Your research, in collaboration and with support of team members, may lead to scientific publications. You will also get a good hands-on perspective at the frontier of machine intelligence and its applications in an interdisciplinary research group and environment.​

Faculty Name

Jesper Tegner

Field of Study

Computer Science, Applied Mathematics