Stochastic Relational AI at KI-2018

The 41st German Conference on Artificial Intelligence

September 24-28th, 2018, Berlin, Germany

Tanya
Braun is a research associate at Universität zu
Lübeck,

Kristian Kersting is a professor
for Machine Learning at
Darmstadt University, and

Ralf Möller is a professor for
Information Systems at Universität zu Lübeck

Probabilistic relational modeling for artificial intelligence (also called stochastic relational AI) has attracted the interest of a huge number of researchers in the last ten years. Assuming a background in probability theory as well as in basics about Bayesian or Markovian networks, we shortly introduce specific probabilistic relational modeling approaches and focus on exact and approximative inference algorithms. Recent developments in the area of learning techniques will be presented as well.

- Introduction (Kristian)
- StarAI
- SystemsAI

- Probabilistic relational modeling (Ralf)
- Semantics (grounded-distributional, density-based, maximum entropy based)
- Inference problems and applications
- Algorithms and systems
- Scalability
- Lmited expressivity: probabilistic databases
- Knowledge compilation: linear programming and weighted model counting
- Approximation: belief propagation, TensorLog

- Scalability by lifting
- Exact lifted inference (Tanya)
- Lifted Junction Tree Algorithm
- Lifted Dynamic Juntion Tree Algorithm

- Approximate lifted inference (Kristian)

- Exact lifted inference (Tanya)
- Learning (Kristian)
- Parameter learning (stochastic gradient descent)
- Structure learning
- Relational reinforcement learning

- Summary (Kristian)