Mathias Niepert will hold a talk on the area of his recent NIPS-Paper "Representation Learning for Visual-Relational Knowledge Graphs" and ICML-Paper "Learning Convolutional Neural Networks for Graphs".
Graph-structured data is ubiquitous and occurs in several
application domains. The talk will provide an overview of graph
representation learning approaches such a graph convolutional networks.
We show that these approaches can be roughly divided in two groups: as
instances of tensor factorization approaches and as algorithms that
learn from local graph structures such as paths and neighborhoods. The
talk will also discuss applications of graph neural networks that we are
currently working on such as polypharmacy and patient outcome prediction.
The meetup takes place in the "Church" at Cyberlab.