Graphs are an incredibly versatile abstraction to represent arbitrary structures such as molecules, relational knowledge or social and traffic networks. This course provides a practical overview of deep (representation) learning on graphs and their applications.
Learning objective
Many established deep learning methods require dense input data with a well-defined structure (e.g. an image, a sequence of word embeddings). However, many practical applications deal with sparsely connected and complex data structures, such as molecules, knowledge graphs or social networks. Graph Neural Networks (GNNs) and general representation learning on graphs have recently experienced a surge in popularity because it addresses the challenge to effectively learn representations over said structures. In this course, we aim to understand the fundamental principles of deep (representation) learning on graphs, the similarities and differences to other concepts in deep learning, as well as the unique challenges from a practical point of view. Finally, we provide an overview of recent applications of graph neural networks.
Content
Introduction to GNN concepts: 1) problem-solving on graphs (node-, edge-, graph-level objectives), structural priors (inductive biases) of graph data, applications for graph learning. 2) Graph Neural Networks: convolutional, attentional, message passing; overview on the zoo of published operators. Relations to Transformers and DeepSets. 3) Expressivity of GNNs. 4) Scalability of Graph Neural Networks: Subsampling, Clustering (Pooling). 5) Augmentations and self-supervised learning on Graphs Application: Drug Discovery, Knowledge graphs, Temporal GNNs, Geometric GNNs, Deep Generative Models for Graphs.
Prerequisites / Notice
263-3210-00 Depp Learning or 263-0008-00 Computational Intelligence Lab; 252-0220-00 Introduction to Machine Learning; Statistics/Probability; Programming in Python; Unix Command Line.
Performance assessment
Performance assessment information (valid until the course unit is held again)
The performance assessment is only offered in the session after the course unit. Repetition only possible after re-enrolling.
Mode of examination
written 120 minutes
Additional information on mode of examination
60% session examination, 40% project/presentation; the final grade will be calculated as a weighted average of both these elements. As a compulsory continuous performance assessment task, the project must be passed on its own and has a bonus/penalty function. The project/presentation is an integral part of the course (30 hours of work, 1 credit) and consists of a practical part and/or a presentation of a research paper. Participation is mandatory. Failing the project results in a failing grade for the overall course examination. Students who fail to fulfil the project/presentation requirement have to de-register from the exam. Otherwise, they are not admitted to the exam and they will be treated as a no-show.
Written aids
1 page (single side) of A4 paper is allowed for notes in the exam. The notes may be typed (font restriction: minimal fon 10 pt) or handwritten.
This information can be updated until the beginning of the semester; information on the examination timetable is binding.
Performance assessment as a semester course