Name	Webedition CMS
Zweck	Dieses Cookie wird vom CMS (Content Management System) Webedition für die unverwechselbare Identifizierung eines Anwenders gesetzt. Es bietet dem Anwender bessere Bedienerführung, z.B. Speicherung von Sucheinstellungen oder Formulardaten. Typischerweise wird dieses Cookie beim Schließen des Browsers gelöscht.
Name	econda
Zweck	Session-Cookie für die Webanalyse Software econda. Diese läuft im Modus „Anonymisiertes Messen“.

Name

Webedition CMS

Zweck

Dieses Cookie wird vom CMS (Content Management System) Webedition für die unverwechselbare Identifizierung eines Anwenders gesetzt. Es bietet dem Anwender bessere Bedienerführung, z.B. Speicherung von Sucheinstellungen oder Formulardaten. Typischerweise wird dieses Cookie beim Schließen des Browsers gelöscht.

Name

econda

Zweck

Session-Cookie für die Webanalyse Software econda. Diese läuft im Modus „Anonymisiertes Messen“.

Name	econda
Zweck	Measure with Visitor Cookie emos_jcvid

Name

econda

Zweck

Measure with Visitor Cookie emos_jcvid

Name	YouTube
Zweck	Zeige YouTube Inhalte
Name	Twitter
Zweck	Twitter Feeds aktivieren

Name

YouTube

Zweck

Zeige YouTube Inhalte

Name

Twitter

Zweck

Twitter Feeds aktivieren

Learning Equivariant and Hybrid Message Passing on Graphs

In this talk I will extend graph neural nets in two directions. First, we will ask if we can formulate a GNN on meshes of two dimensional manifolds. Previous approaches mostly used standard GNNs which are invariant to permutations of the input nodes. However, we show this is unnecessarily restrictive. Instead, we define mesh-CNNs which are equivariant and allow more general kernels. Second we will study how to incorporate information about the data generating process into GNNs. Belief propagation is a form of GNN with no learnable parameters that performs inference in a generative graphical model. We subsequently augment BP by a trainable GNN to correct the mistakes of BP, in order to improve predictive performance. Experiments show the increased power of both methods.

Wednesday, 6th Mai 2020, 11 am

live streaming link: https://www.conf.dfn.de/stream/nr5h8pp6e87k3

Biosketch Dr. Max Welling

Prof. Dr. Max Welling is a research chair in Machine Learning at the University of Amsterdam and a VP Technologies at Qualcomm. He has a secondary appointment as a senior fellow at the Canadian Institute for Advanced Research (CIFAR). He is co-founder of “Scyfer BV” a university spin-off in deep learning which got acquired by Qualcomm in summer 2017. In the past he held postdoctoral positions at Caltech (’98-’00), UCL (’00-’01) and the U. Toronto (’01-’03). He received his PhD in ’98 under supervision of Nobel laureate Prof. G. ‘t Hooft. Max Welling has served as associate editor in chief of IEEE TPAMI from 2011-2015 (impact factor 4.8). He serves on the board of the NIPS foundation since 2015 (the largest conference in machine learning) and has been program chair and general chair of NIPS in 2013 and 2014 respectively. He was also program chair of AISTATS in 2009 and ECCV in 2016 and general chair of MIDL 2018. He has served on the editorial boards of JMLR and JML and was an associate editor for Neurocomputing, JCGS and TPAMI. He received multiple grants from Google, Facebook, Yahoo, NSF, NIH, NWO and ONR-MURI among which an NSF career grant in 2005. He is recipient of the ECCV Koenderink Prize in 2010. Welling is in the board of the Data Science Research Center in Amsterdam, he directs the Amsterdam Machine Learning Lab (AMLAB), and co-directs the Qualcomm-UvA deep learning lab (QUVA) and the Bosch-UvA Deep Learning lab (DELTA). Max Welling has over 250 scientific publications in machine learning, computer vision, statistics and physics and an h-index of 62.

https://staff.fnwi.uva.nl/m.welling/

Joint event with heidelberg.ai