The Data and Web Science seminar covers recent topics in data and web science. This term the seminar focuses on Relational Learning.
In this seminar, you will
If you are an MSc student, register via Portal 2 until 1 March. If you are a BSC student, register via email to Adrian Kochsiek until 1 March.
If you are accepted into the seminar, provide at least 4 topics of your preference (your own and/
Each student works on a topic within the area of the seminar along with an accompanying reference paper. Your presentation and report should explore the topic with an emphasis on the reference paper, but not just the reference paper.
We provide example topics and reference papers below. We structured the topics into three blocks: symbolic, neural and neural-symbolic approaches. You can get an overview of relational machine learning approaches on knowledge graphs here and in specific neural approaches here. Each topic is associated with an example reference paper. If you want, you may suggest a different reference paper (let us know after the topic assignment) or a different topic within the relational learning area (talk to us before the topic assignments).
1. Inductive Logic Programming (BSc students only)
Inductive Logic Programming in a Nutshell
Introduction to Statistical Relational Learning (Ch 3), 2007
2. Markov Logic Networks
Richardson et al.
Markov Logic Networks
Machine Learning, 2006
3. Rule Learning
Galárraga et al.
AMIE: Association Rule Mining under Incomplete Evidence in Ontological Knowledge Bases
4. Incremental Rule Learning
Zhou et al.
Mining Rules Incrementally over Large Knowledge Bases
5. Knowledge Graph Embeddings with Translational Distance Models
Sun et al.
Rotate: Knowledge Graph Embedding by Relational Rotation in Complex Space
6. Knowledge Graph Embeddings with Matrix Factorization
Trouillon et al.
Complex Embeddings for Simple Link Prediction
7. Knowledge Graph Embeddings with Graph Neural Networks
Schlichtkrull et al.
Modeling Relational Data with Graph Convolutional Networks
8. Temporal Knowledge Graph Completion
Goel et al.
Diachronic Embedding for Temporal Knowledge Graph Completion
9. Reasoning with Neural Tensor Networks
Socher et al.
Reasoning with Neural Tensor Networks for Knowledge Base Completion
10. Visual Relationship Detection
Chen et al.
Knowledge-Embedded Routing Network for Scene Graph Generation
11. Differentiable Inductive Logic Programming
Evans et al.
Learning Explanatory Rules from Noisy Data
Journal of Artificial Intelligence Research, 2018
12. Differentiable Rule Mining
Sadeghian et al.
DRUM: End-to-End Differentiable Rule Mining On Knowledge Graphs
13. End to End Differentiable Reasoning
Minervini et al.
Differentiable Reasoning on Large Knowledge Bases and Natural Language
14. Joint Rule and Embedding Learning
Ho et al.
Rule Learning from Knowledge Graphs Guided by Embedding Models
Tracking cookies are currently allowed.
Tracking cookies are currently not allowed.