Graph-structured data is ubiquitous across application domains ranging from chemo- and bioinformatics to image and social network analysis. To develop successful machine learning algorithms, we need techniques that map the rich information inherent in the graph structure to a vectorial representation in a meaningful way—so-called graph embeddings. Designing such embeddings comes with unique challenges. The embedding has to account for the complex structure of (real-world) networks and additional high-dimensional continuous vectors attached to nodes and edges in a (permutation) invariant way while being scalable to massive graphs or sets of graphs. Moreover, when used in supervised machine learning, the model trained with such embeddings must generalize well to new or previously unseen (graph) instances. Hence, more abstractly, designing graph embeddings results in a trade-off between (1) expressivity, (2) scalability, and (3) generalization. In this seminar, we want to discuss the current progress on the theoretical foundations of machine learning on graphs, penetrating the above-listed three challenges.

To pass the seminar, you need to fulfill the following:

- Give a 30-minute-long talk about your assigned paper.
- Write a 12- to 15-page detailed report about your assigned paper.
- Peer-review your fellow students' reports.
- Attend all meetings and actively participate; see below for dates.

- More details are given during the mandatory kick-off meeting.
- Papers will be assigned after the kick-off meeting.
- The long talks will be presented in day-long block seminar.
**All meetings (kick-off and final talks) will take place in Room 228, Theaterstraße 35 - 39.**

Date | |
---|---|

14.10.2022, 10:00 | Kick-off meeting |

10.11.2022, 24:00 | Submission of report drafts |

09.12.2022, 24:00 | Submission of reports for peer review |

20.12.2022, 24:00 | Submission of peer reviews |

09.01.2023, 24:00 | Submission of reports |

16.01.2023, 24:00 | Feedback by the organizers |

25.01.2023, 24:00 | Submission of of presentation slides |

31.01.2023, 24:00 | Submission of final reports |

16.02.2023, 10:00 | Talks |

- Equivariant Subgraph Aggregation Networks
- Provably Powerful Graph Networks
- Weisfeiler and Leman Go Sparse: Towards Scalable Higher-order Graph Embeddings
- Weisfeiler and Leman Go Walking: Random Walk Kernels Revisited
- Graph Neural Networks with Local Graph Parameters
- Generalization and Representational Limits of Graph Neural Networks
- Agent-based Graph Neural Networks
- What Functions Can Graph Neural Networks Generate?
- Affinity-Aware Graph Networks