IE 689 Relational Learning

Participants will be introduced to a specific form of Machine Learning that aims at learning relational rules from relational data. They should understand the strengths and limitations of this type of machine learning methods in comparison to more widely used propositional learning approaches  and  gather  practical  experiences  with  using  the  methods  on example data.

Recommended Knowledge:

  • Data Mining
  • First-Order Logic
  • Problem Solving as Search

Dates

Lecture and Tutorial are alternating each Monday at 12:00-13:30 in A203, B 6, 23-25

ILIAS and Registration

The course uses ILIAS. Any further information can be found there.
You can register for the course via the portal.

Assessments

  • Written examination.
  • Admission requirement: Successful participation in the exercises (>50% on each homework as-
    signment)

Instructors

  • Lecture: Prof. Dr. Heiner Stuckenschmidt
  • Tutorial: Dr. Christian Meilicke / Manuel Fink

Literature

Luc De Raedt. Logical and Relational Learning. Springer 2010. Chapters 1-6.

Galarraga et al.: AMIE: association rule mining under incomplete evidence in ontological knowledge bases.Proceedings of the 22nd international conference on World Wide Web. Pages 413--422, ACM, 2013.