[Solomonov Seminar] 286. Solomonov seminar

[Marko Grobelnik]

V sredo, 21. novembra 2018 bo ob 16h v Veliki predavalnici IJS 286. 
Solomonov seminar. Velika predavalnica je v prvem nadstropju glavne 
stavbe IJS na Jamovi 39. Posnetki preteklih seminarjev so na 
http://videolectures.net/solomon/

Tokrat bo predaval Jure Leskovec s tematiko, ki povezuje grafe/omrezja z 
globokim ucenjem (angl. deep learning) - v zadnjem casu ima Jure nekaj 
dobrih rezultatov pri analizi grafov z modernimi metodami ucenja, ki jih 
bo predstavil na seminarju.

Seminar je ob nekoliko bolj pozni uri zaradi objektivnih omejitev.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Jure Leskovec, Stanford University/Pinterest/IJS

TITLE: Deep Learning on Graphs

ABSTRACT: Machine learning on graphs is an important and ubiquitous task 
with applications ranging from drug design to friendship recommendation 
in social networks. The primary challenge in this domain is finding a 
way to represent, or encode, graph structure so that it can be easily 
exploited by machine learning models. However, traditionally machine 
learning approaches relied on user-defined heuristics to extract 
features encoding structural information about a graph. In this talk I 
will discuss methods that automatically learn to encode graph structure 
into low-dimensional embeddings, using techniques based on deep learning 
and nonlinear dimensionality reduction. I will provide a conceptual 
review of key advancements in this area of representation learning on 
graphs, including random-walk based algorithms, and graph convolutional 
networks. We will discuss applications to web-scale recommender systems, 
healthcare and knowledge representation and reasoning.