Hasso-Plattner-InstitutSDG am HPI
Hasso-Plattner-InstitutDSG am HPI
Login
 

Graph Neural Networks - Applications & Link to Graph Queries (Wintersemester 2021/2022)

Dozent: Prof. Dr. Holger Giese (Systemanalyse und Modellierung) , Christian Medeiros Adriano (Systemanalyse und Modellierung) , Matthias Barkowsky (Systemanalyse und Modellierung)

Allgemeine Information

  • Semesterwochenstunden: 4
  • ECTS: 6
  • Benotet: Ja
  • Einschreibefrist: 01.10.-22.10.2021
  • Lehrform: Projekt / Seminar
  • Belegungsart: Wahlpflichtmodul
  • Lehrsprache: Englisch

Studiengänge & Module

Data Engineering MA
Digital Health MA
IT-Systems Engineering MA
  • OSIS-Konzepte und Methoden
  • OSIS-Techniken und Werkzeuge
  • OSIS-Spezialisierung
  • SAMT-Konzepte und Methoden
  • SAMT-Techniken und Werkzeuge
  • SAMT-Spezialisierung

Beschreibung

Graph Neural Networks are a set of novel techniques aimed at enabling deep neural networks to work on heterogeneous graphs, e.g., social networks, knowledge graphs, recommender systems, gene regulatory networks, traffic networks, etc. These heterogeneous graphs became central components of complex software systems, which make predictions and interventions on the structure and behavior of the system and its context (e.g., users, environment). Take for instance, the mitigation of the spread of an event (accident, rumors, disease) through a network (traffic, social network). The heterogeneous network would model the current state of connections, their strength, and multiple properties in their nodes and edges. This complex data would be used to  predict the propagation paths and indicate the best set of nodes to intervene to mitigate the spread of rumors or disease and its effect on a system as a whole (traffic, population). Interventions can involve changes in the connections (isolate, circumvent, shortcut) and the attributes of the nodes (duplicate, reset, extend).

Note however, that neural networks algorithms were initially developed to solve problems in the domains of computer vision (3D and 2D) and natural language processing (1D). These domains present Euclidean spaces that allow neural networks to leverage on the regularities inherent to coordinate systems, vector space structures, or fixed distributions. Because these regularities are not guaranteed to be present in heterogeneous networks, new extensions were developed to these algorithms.

In this seminar we will study extensions to neural networks and apply them to heterogeneous graphs of real-world problems. We will tackle these domain-specific problems in a principled way by solving the more generic graph-related problems of node classification, structure discovery, path identification, subgraph generation. 

Topics:

  • Theory
    • Graph Theory
    • Graph Queries
  • Probabilistic Graph Networks 
    • Bayesian Networks 
    • Markov Networks (Relational Learning) 
    • Propagation Networks 
  • Graph Neural Networks 
    • Descriptive Graph Models
      • Graph Structural Features  (Metrics, Clustering)
      • Graph Data (GraphQL, GraphDB)
      • Graph Simulation (Generative Models, Random Models)
    • Prediction Graph Models
      • Graph Embeddings - Message Passing
      • Graph Convolutional Networks
      • Graph Attention Networks
    • Control Graph Models
      • Evolution of Graphs and Temporal Networks
      • Mitigation of Event Propagation
      • Maximization of Network Influence
      • Causal Interventions on Graph Neural Networks

Literatur

Zhou, J. et al., 2018, Graph neural networks: A review of methods and applications.

 Xu, K., et al., 2018, How powerful are graph neural networks? 

Liu, Z., et al., 2020, Introduction to Graph Neural Networks, Synthesis Lectures on Artificial Intelligence and Machine Learning) 

Leng, S., et al., 2019, Reconstructing directional causal networks with random forest: Causality meeting machine learning. Chaos: An Interdisciplinary Journal of Nonlinear Science, 29(9), 093130

Ke, N. R., et al., 2019)Learning neural causal models from unknown interventions.

Y. Yu, et al., 2019, Dag-gnn: Dag structure learning with graph neural networks.

Z. Wu, et al., 2020, A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems.

Park, J., 2021, GraphDB and Graph Neural Network, blog.kc-ml2.com/graphdb-and-graph-neural-network/

Lern- und Lehrformen

The course is a project seminar, which has an introductory phase comprising initial short lectures. After that, the students will work in groups on jointly identified experiments applying specific solutions to given problems and finally prepare a presentation and write a report about their findings concerning the experiments.

We will organize this project seminar as a hybrid event, allowing students to participate online as well as in person.

After the registration with the Studienreferat via Moodle and before the first meeting, we will query the participants to check who prefers which format. Generally, we recommend in-person meetings for the introductory meeting and the final presentations and discussion, and an online format for intermediate lectures and project meetings, but we will try to accommodate all wishes. In case you have any questions, please contact christian.adriano(at)hpi.de.

Leistungserfassung

We will grade the group's experiments (60%), reports (30%), and presentations (10%). Participation in the project seminar during meetings and other groups' presentations in the form of questions and feedback will also be required.

Termine

If you are interested in this course, please register with the Studienreferat (via Moodle poll) until 22.10. We consider your registration an expression of interest and will allow you to cancel your registration after the introductory meeting.

If you have any question on the course organization or want to register after the Studienreferat’s deadline, please contact christian.adriano(at)hpi.de 

Start date: October 27 at 13:30

Room (for in-person): HS 3

Zoom credentials (for online participants): link

Task assignments date: On November 23 and 24, we will jointly discuss the project tasks based on the topics and the students' individual interests.

Zurück